[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-wenhwu--awesome-remote-sensing-change-detection":3,"tool-wenhwu--awesome-remote-sensing-change-detection":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",138956,2,"2026-04-05T11:33:21",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":70,"readme_en":71,"readme_zh":72,"quickstart_zh":73,"use_case_zh":74,"hero_image_url":75,"owner_login":76,"owner_name":77,"owner_avatar_url":78,"owner_bio":79,"owner_company":77,"owner_location":77,"owner_email":80,"owner_twitter":77,"owner_website":77,"owner_url":81,"languages":77,"stars":82,"forks":83,"last_commit_at":84,"license":77,"difficulty_score":85,"env_os":86,"env_gpu":87,"env_ram":87,"env_deps":88,"category_tags":91,"github_topics":92,"view_count":23,"oss_zip_url":77,"oss_zip_packed_at":77,"status":16,"created_at":98,"updated_at":99,"faqs":100,"releases":131},2381,"wenhwu\u002Fawesome-remote-sensing-change-detection","awesome-remote-sensing-change-detection","A comprehensive and up-to-date compilation of datasets, tools, methods, review papers, and competitions for remote sensing change detection.","awesome-remote-sensing-change-detection 是一个专注于遥感变化检测领域的开源资源合集，旨在为相关研究与开发提供一站式导航。它系统性地整理了该领域最新的数据集、工具代码、核心算法方法、综述论文以及各类竞赛信息，帮助从业者快速掌握前沿动态。\n\n在遥感应用中，如何从卫星或航空影像中精准识别地表变化（如建筑物增减、灾害损毁、土地利用变迁等）一直是个技术难点，往往面临数据分散、算法复现困难等问题。awesome-remote-sensing-change-detection 通过汇聚全球优质资源，有效解决了信息碎片化难题，大幅降低了入门门槛和调研成本。\n\n这份合集特别适合遥感领域的科研人员、算法工程师以及深度学习开发者使用。无论是需要寻找特定场景的训练数据，还是希望对比不同模型的性能，都能在这里找到详尽的索引。其独特的技术亮点在于不仅涵盖了传统的 CNN 方法，还及时跟进并收录了基于基础模型（Foundation Models）、扩散模型（Diffusion Models）以及 Transformer 架构的最新前沿成果，同时区分了光学影像与多模态（如 SA","awesome-remote-sensing-change-detection 是一个专注于遥感变化检测领域的开源资源合集，旨在为相关研究与开发提供一站式导航。它系统性地整理了该领域最新的数据集、工具代码、核心算法方法、综述论文以及各类竞赛信息，帮助从业者快速掌握前沿动态。\n\n在遥感应用中，如何从卫星或航空影像中精准识别地表变化（如建筑物增减、灾害损毁、土地利用变迁等）一直是个技术难点，往往面临数据分散、算法复现困难等问题。awesome-remote-sensing-change-detection 通过汇聚全球优质资源，有效解决了信息碎片化难题，大幅降低了入门门槛和调研成本。\n\n这份合集特别适合遥感领域的科研人员、算法工程师以及深度学习开发者使用。无论是需要寻找特定场景的训练数据，还是希望对比不同模型的性能，都能在这里找到详尽的索引。其独特的技术亮点在于不仅涵盖了传统的 CNN 方法，还及时跟进并收录了基于基础模型（Foundation Models）、扩散模型（Diffusion Models）以及 Transformer 架构的最新前沿成果，同时区分了光学影像与多模态（如 SAR）数据资源，展现了极高的专业度与时效性。对于想要深入探索遥感智能解译的用户而言，这是一个不可或缺的权威参考库。","# \u003Cp align=center>`Awesome Remote Sensing Change Detection`\u003C\u002Fp>\n[![Awesome](https:\u002F\u002Fcdn.rawgit.com\u002Fsindresorhus\u002Fawesome\u002Fd7305f38d29fed78fa85652e3a63e154dd8e8829\u002Fmedia\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fsindresorhus\u002Fawesome) [![Maintenance](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FMaintained%3F-yes-green.svg)](https:\u002F\u002FGitHub.com\u002FNaereen\u002FStrapDown.js\u002Fgraphs\u002Fcommit-activity) [![PR's Welcome](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-welcome-brightgreen.svg?style=flat)](http:\u002F\u002Fmakeapullrequest.com) [![made-with-Markdown](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FMade%20with-Markdown-1f425f.svg)](http:\u002F\u002Fcommonmark.org)![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fwenhwu\u002Fawesome-remote-sensing-change-detection?style=social)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwenhwu\u002Fawesome-remote-sensing-change-detection?style=social)![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fwenhwu\u002Fawesome-remote-sensing-change-detection.svg?style=flat&logo=github&label=Last%20Commit)[![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-blue.svg)](https:\u002F\u002Fopensource.org\u002Flicenses\u002FMIT)\n\nA comprehensive and up-to-date compilation of datasets, tools, methods (including foundation models, diffusion models, transformers, and CNNs), review papers, and competitions for remote sensing change detection.\n\n# Contents\n\n- [Datasets](#datasets)\n  - [Optical Datasets](#optical-datasets)\n  - [Multi-Modal and SAR Datasets](#multi-modal-and-sar-datasets)\n- [Tools](#tools)\n- [Methods](#methods)\n  - [Deep Learning](#deep-learning)\n    - [Foundation Models](#foundation-models)\n    - [Diffusion Models and GANs](#diffusion-models-and-gans)\n    - [Transformers](#transformers)\n    - [CNNs](#cnns)\n  - [Traditional Methods](#traditional-methods)\n    - [Common Methods](#common-methods)\n    - [New Methods](#new-methods)\n- [Review Papers](#review-papers)\n- [Competitions](#competitions)\n- [Satellite Data Resources for Disaster Response](#satellite-data-resources-for-disaster-response)\n- [More Resources](#more-resources)\n- [Citation](#citation)\n\n\n# Datasets\n\n* SCD: Semantic Change Detection, BCD: Binary Change Detection, DDA: Disaster Damage Assessment, BDA: Building Damage Assessment, RSICC: Remote Sensing Image Change Captioning\n\n## Optical Datasets\n\n|Year|Task|Target| Dataset |Publication|Source|Image Pairs |Image Size|Resolution|Location|Class|\n|:---|:--- |:--- | :------| :------|:----------| :-------| :-------| :----------- | :----- | :---- |\n|2025|SCD+BCD|Building|[RSCC](https:\u002F\u002Fgithub.com\u002FBili-Sakura\u002FRSCC)|[NeurIPS2025](https:\u002F\u002Fopenreview.net\u002Fforum?id=yn2fJYBKEB)|Open Maxar Data Programme |62,351|512 × 512|0.3-0.8m|31 Locations Globally|5|\n|2026|SCD|Land cover|[LsSCD-Ex](https:\u002F\u002Fgithub.com\u002Ftangkai-RS\u002FDreamCD)|[JAG2026](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.jag.2026.105125)|Google Earth|100|2048 × 2048|0.6m|Nanjing, China|8|\n|2026|SCD+BCD|Building|[FOTBCD-Binary;FOTBCD-Instances](https:\u002F\u002Fgithub.com\u002Fabdelpy\u002FFOTBCD-datasets)|[arXiv2026](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.22596)|IGN|27,871;4000|512 × 512|0.2m|France|2;3|\n|2025|RSICC|Land cover|[MOSAIC-SEN2-CC](https:\u002F\u002Fgithub.com\u002FChangeCapsInRS\u002FMOSAIC-SEN2-CC)|[JSTARS2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11181102\u002F)|Sentinel-2|5,232|480 × 480|10m|Global|8|\n|2025|SCD|Cropland|[Xiamen](https:\u002F\u002Fgithub.com\u002Flong123524\u002FCPGNet), [Fuzhou](https:\u002F\u002Fgithub.com\u002Flong123524\u002FHGINet-torch)|[JAG2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1569843225005631?dgcid=rss_sd_all), [ISPRS P&RS 2024](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271624001709)|Google Earth|6480 (Xiamen); 8719 (Fuzhou)|256 × 256|0.5m|Xiang’an and Tong’an districts, Xiamen, China; Changle and Minhou districts, Fuzhou, China|7|\n|2025|SCD+BCD|Land cover|[WHU-GCD](https:\u002F\u002Fgpcv.whu.edu.cn\u002Fdata\u002FWHU_Generative_Change_Detection_Dataset.html)|[ISPRS P&RS 2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271625001595?dgcid=rss_sd_all)|LoveDA, Evlab-SS, LandCover.ai, and Google Earth; DSIFN-CD,LEVIR-CD, SECOND, CLCD, CNAM-CD|28,067|512 × 512|-|Global|26|\n|2025|BCD|Building|[CWSCD](https:\u002F\u002Fgithub.com\u002Fyuruqingsi\u002FCWSCD-dataset)|[JAG2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1569843225005084?dgcid=rss_sd_all)|BJ-2, GF-2|200|2048×2048|1m|Hebei, China|2|\n|2025|BCD|Building|DVCD|[arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.17944)|Drone Images|12,833|-|0.1m|Guangdong, China|2|\n|2025|SCD|Land cover|[SC-SCD7, CC-SCD5](https:\u002F\u002Fgithub.com\u002FStephenApX\u002FMTL-TripleS)|[ISPRS P&RS 2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271625003776?dgcid=rss_sd_all)|Pléiades, Beijing-2, Gaofen-1, Gaofen-2, Ziyuan-3|1,722; 953|512×512|0.5m, 2.3m, 2.5 m|Zhangzhou (Longwen) and Henan (Dengfeng, Luoyang, Sanmenxia), China |8; 5|\n|2025|SCD|Land cover|[LevirSCD](https:\u002F\u002Fgithub.com\u002Fzmoka-zht\u002FFoBa)|[arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.15788)|GF-1, Google Earth|3,225|256×256|1-2|Beijing, China|16|\n|2025|BCD|Land cover|[JL1-CD](https:\u002F\u002Fgithub.com\u002FcircleLZY\u002FMTKD-CD)|[arXiv2025](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2502.13407)|Jilin-1|5,000|512×512|0.5-0.75m|Multiple provinces in China|2|\n|2025|SCD|Building|[EBD](https:\u002F\u002Ffigshare.com\u002Farticles\u002Ffigure\u002FAn_Extended_Building_Damage_EBD_dataset_constructed_from_disaster-related_bi-temporal_remote_sensing_images_\u002F25285009\u002F2)| [JRS2025](https:\u002F\u002Fspj.science.org\u002Fdoi\u002Ffull\u002F10.34133\u002Fremotesensing.0733?af=R)|WorldView-3|>18,000|512×512|0.3-0.5m|Global|7|\n|2025|SCD|Land use|[MLCD](https:\u002F\u002Faistudio.baidu.com\u002Fdataset\u002Fdetail\u002F245516\u002Fintro)|[JSTARS2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11058393)|Google Earth Engine|10, 000|256×256|0.5-2m|Macao, China|\n|2024|BCD|Mine| [MineNetCD](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FHZDR-FWGEL\u002FMineNetCD256) |[TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10744421) |Google Earth|71,711|256×256| 1.2m |Global|2|\n|2024|BCD|Building| [TUE-CD](https:\u002F\u002Fgithub.com\u002FRSMagneto\u002FMSI-Net)| [TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10623278)|WorldView-2|1,656|256×256|1.8m|Turkey|2|\n|2024|SCD|Urban|[MSRS-CD](https:\u002F\u002Fgithub.com\u002Fbobo59\u002FMSRSCD)|[JSTARS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10813409)|-|841|1,024×1,024|0.5m|Southern Chinese cities|5|\n|2024|SCD|Cropland| [CropSCD](https:\u002F\u002Fgithub.com\u002Flsmlyn\u002FCropSCD)| [TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10579791) |-|4,141|512×512|0.5-2m|Guangdong, China|9|\n|2024|SCD|Cropland| [Hi-CNA](https:\u002F\u002Frsidea.whu.edu.cn\u002FHi-CNA_dataset.htm) |[ISPRS P&RS 2024](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271624002090) |GF-2|6,797| 512×512|0.8m|China (Hebei, Shanxi, Shandong, and Hubei) |5|\n|2024|SCD|Land cover|[ChangNet](https:\u002F\u002Fgithub.com\u002Fjankyee\u002FChangeNet)| [ICASSP2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10446592)|WayBack|31,000|1,900×1,200|0.3m|100 Cities in China|6|\n|2023|SCD|Cropland|[JL1](https:\u002F\u002Fwww.jl1mall.com\u002Fresrepo\u002F?fromUrl=https:\u002F\u002Fwww.jl1mall.com\u002Fedu)|-|Jilin-1|8,000 | 256×256 |\u003C0.75m|-|9|\n|2023|BCD|Building| [EGY-BCD](https:\u002F\u002Fgithub.com\u002Foshholail\u002FEGY-BCD)| [GRSL2023](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10145434)|Google Earth |6,091 | 256×256| 0.25m| Egypt|2|\n|2023|BCD|Building| [HRCUS-CD](https:\u002F\u002Fgithub.com\u002Fzjd1836\u002FAERNet)| [TGRS2023](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10209204)|-|11,388 |256×256| 0.5m|Zhuhai, China|2|\n|2023|BCD|Building| [SI-BU](https:\u002F\u002Fvrlab.org.cn\u002F~hanhu\u002Fprojects\u002Fbcenet\u002F)| [ISPRS P&RS 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271623001284?via%3Dihub)|Google Earth|4,932|512×512| 0.2m| Guiyang, China|2|\n|2023|SCD|Land cover|[CNAM-CD](https:\u002F\u002Fgithub.com\u002FSilvestezhou\u002FCNAM-CD)| [RS2023](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F15\u002F9\u002F2464)|Google Earth|2,503|512×512|0.5m|12 State-level New Areas in China|6|\n|2023|SCD|Land cover| [WUSU](https:\u002F\u002Frsidea.whu.edu.cn\u002Fresource_wusu_sharing.htm)| [IJDE2023](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F17538947.2023.2246445)|GF-2|3| 6,358×6,382 \u002F 7,025×5,500| 1m |Wuhan, China|12|\n|2023|BCD|Landslide| [GVLM](https:\u002F\u002Fgithub.com\u002Fzxk688\u002FGVLM)| [ISPRS P&RS 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271623000242)|Google Earth|17| 1,748×1,748-10,808×7,424|0.59m|Global|2|\n|2023|SCD|Building|[BANDON](https:\u002F\u002Fgithub.com\u002Ffitzpchao\u002FBANDON)| [Sci. China Inf. Sci. 2023](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs11432-022-3691-4)|Google Earth, Microsoft Virtual Earth, and ArcGIS|2,283|2,048×2,048| 0.6m|China (Beijing, Shanghai, Wuhan, Shenzhen, Hong Kong, and Jinan)|6|\n|2023|SCD|Land cover| [DynamicEarthNet](https:\u002F\u002Fmediatum.ub.tum.de\u002F1650201) | [CVPR2022](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2022\u002Fhtml\u002FToker_DynamicEarthNet_Daily_Multi-Spectral_Satellite_Dataset_for_Semantic_Change_Segmentation_CVPR_2022_paper.html) |PlanetFusion|54,750|1,024×1,024|3m|Global|7|\n|2022|BCD|Road|[CRCD, WRCD](http:\u002F\u002Fwww.lmars.whu.edu.cn\u002Fsuihaigang\u002Findex)|[TITS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9815123)|Aerial Images, Google Earth|3,237, 1,960|512×512|0.2m, 1.14m|Christchurch, New Zealand; Jiangxia, Wuhan, China|2|\n|2022|BCD|Cropland| [CLCD](https:\u002F\u002Fgithub.com\u002Fliumency\u002FCropLand-CD)| [JSTARS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9780164)|GF-2|600|512×512|0.5-2m|Guangdong, China|2|\n|2022|RSICC|Building | [LEVIR-CC](https:\u002F\u002Fgithub.com\u002FChen-Yang-Liu\u002FRSICC)  | [TGRS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9934924)|Google Earth|10,077| 1,024×1,024| 0.5m| Texas, USA|2|\n|2022|BCD|Land cover | [SYSU-CD](https:\u002F\u002Fgithub.com\u002Fliumency\u002FSYSU-CD)    | [TGRS2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9467555) |-|20,000| 256×256 | 0.5m |Hong Kong, China |2|\n|2022|SCD|Building| [S2Looking](https:\u002F\u002Fgithub.com\u002FS2Looking\u002FDataset)|[RS2021](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F13\u002F24\u002F5094) |GF, SuperView, BJ-2|5,000| 1,024×1,024| 0.5-0.8m| Global|2|\n|2022|BCD|Building| [LEVIR-CD+](https:\u002F\u002Fgithub.com\u002FS2Looking\u002FDataset)|[RS2021](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F13\u002F24\u002F5094) |Google Earth|985|1,024×1,024|0.5m|Texas, USA|2|\n|2022|SCD|Land cover| [Landsat-SCD](https:\u002F\u002Ffigshare.com\u002Farticles\u002Ffigure\u002FLandsat-SCD_dataset_zip\u002F19946135\u002F1)|[IJDE2022](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F17538947.2022.2111470) |Landsat|8,468|416×416|30m|Xinjiang, China|10|\n|2022|SCD|Building|[NanjingDataset](https:\u002F\u002Fgithub.com\u002FSianGIS\u002FNanjingDataset)|[ISPRS P&RS 2022](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271622001344) |Google Earth|2,519|256×256|0.3m|Nanjing, China|3|\n|2022|RSICC|Urban|[Dubai-CC](https:\u002F\u002Fdisi.unitn.it\u002F~melgani\u002Fdatasets.html)|[TGRS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9847254)|Landsat 7|500|50×50|30m|Dubai|6|\n|2022|SCD|Flood|[SpaceNet 8](https:\u002F\u002Fjoin.topcoder.com\u002Fspacenet) | [CVPR2022W](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2022W\u002FEarthVision\u002Fpapers\u002FHansch_SpaceNet_8_-_The_Detection_of_Flooded_Roads_and_Buildings_CVPRW_2022_paper.pdf)|Maxar| 12 | 1,300×1,300 | 0.3-0.8m |Germany, and Louisiana|4|\n|2021|SCD|Land cover|[MSD](https:\u002F\u002Fwww.grss-ieee.org\u002Fcommunity\u002Ftechnical-committees\u002F2021-ieee-grss-data-fusion-contest-track-msd\u002F)|[JSTARS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9690575)|NAIP, Landsat-8, and NLCD|2,250|-|1m, 30m|Maryland, USA|16|\n|2021|SCD|Land cover| [S2MTCP](https:\u002F\u002Fzenodo.org\u002Frecords\u002F4280482)|[ICPR2021](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-68787-8_42) |Sentinel-2|1,520|600×600|10m|Global|-|\n|2021|BCD|Urban|[HTCD](https:\u002F\u002Fgithub.com\u002FShaoRuizhe\u002FSUNet-change_detection) |[RS2021](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F13\u002F18\u002F3750\u002Fhtm)|Google Earth, Open Aerial Map|3,772|256×256, 2,048×2,048|0.5971m, 0.07465m|Chisinau, Moldova|2|\n|2020|BCD|Building| [GZ-CD](https:\u002F\u002Fgithub.com\u002Fdaifeng2016\u002FChange-Detection-Dataset-for-High-Resolution-Satellite-Imagery) (or CD_Data_GZ)|[TGRS2020](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9161009)|Google Earth|19| 1,006×1,168-4,936×5,224| 0.55m| Guangzhou, China|2|\n|2020|BCD|Building| [DSIFN](https:\u002F\u002Fgithub.com\u002FGeoZcx\u002FA-deeply-supervised-image-fusion-network-for-change-detection-in-remote-sensing-images\u002Ftree\u002Fmaster\u002Fdataset) (or DSIFN-CD)|[ISPRS P&RS 2020](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271620301532?via%3Dihub) |Google Earth|3,940 | 512×512|-|China (Beijing, Chengdu, Shenzhen, Chongqing, Wuhan, and Xian)|2|\n|2020|BCD|Building| [LEVIR-CD](https:\u002F\u002Fjustchenhao.github.io\u002FLEVIR\u002F)| [RS2020](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F12\u002F10\u002F1662)|Google Earth|637| 1,024×1,024|0.5m|Texas, USA|2|\n|2020|SCD|Land cover| [Hi-UCD](https:\u002F\u002Fgithub.com\u002FDaisy-7\u002FHi-UCD-S?tab=readme-ov-file)|[arXiv2020](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.03247) |Aerial Images|1,293|1,024×1,024|0.1m|Tallinn, Estonia|9|\n|2020|SCD|Land cover| [SECOND](https:\u002F\u002Fcaptain-whu.github.io\u002FSCD\u002F)| [TGRS2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9555824) |Aerial Images |4,662|512×512| -  |China (Hangzhou, Chengdu, and Shanghai)|6|\n|2020|BCD| Building | [MUDS](https:\u002F\u002Fmedium.com\u002Fthe-downlinq\u002Fthe-spacenet-7-multi-temporal-urban-development-challenge-dataset-release-9e6e5f65c8d5) (or SpaceNet 7) | [CVPR2021](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2021\u002Fpapers\u002FVan_Etten_The_Multi-Temporal_Urban_Development_SpaceNet_Dataset_CVPR_2021_paper.pdf)|-| -|1,024×1,024|4m|Global|2|\n|2019|BDA|Building| [xBD](https:\u002F\u002Fxview2.org\u002Fdataset) | [arXiv2019](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.09296) |Maxar| 11,034 | 1,024×1,024 | \u003C0.8m |Global|4|\n|2019|SCD|Land cover| [HRSCD](https:\u002F\u002Fieee-dataport.org\u002Fopen-access\u002Fhrscd-high-resolution-semantic-change-detection-dataset)| [CVIU2019](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1077314219300992) |IGN|291|10,000×10,000|0.5m|France (Rennes, and Caen)|5|\n|2018|BCD|Building| [WHU-CD](https:\u002F\u002Fstudy.rsgis.whu.edu.cn\u002Fpages\u002Fdownload\u002Fbuilding_dataset.html)| [TGRS2018](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8444434)|Aerial Image|1|32,507×15,354|0.2m| Christchurch, New Zealand|2|\n|2018|BCD|Building| [CDD](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1GX656JqqOyBi_Ef0w65kDGVto-nHrNs9\u002Fedit?pli=1) (or SVCD)| [Int. Arch. Photogramm. Remote Sens. Spatial Inf. 2018](https:\u002F\u002Fisprs-archives.copernicus.org\u002Farticles\u002FXLII-2\u002F565\u002F2018\u002Fisprs-archives-XLII-2-565-2018.pdf) |Google Earth|1,6000| 256×256| 0.03-1m |-|2|\n|2018|BCD|Riverway| [The River Data Set](https:\u002F\u002Fshare.weiyun.com\u002F5xdge4R)|[TGRS2018](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8418840)|EO-1 Hyperion|1|463×241|30m|Jiangsu, China|2|\n|2018|BCD|Land cover|[OSCD](https:\u002F\u002Fieee-dataport.org\u002Fopen-access\u002Foscd-onera-satellite-change-detection)|[IGARSS2018](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8518015)|Sentinel-2|24|600×600|10-60m|Global|2|\n|2008|BCD|Land cover|[SZTAKI](http:\u002F\u002Fweb.eee.sztaki.hu\u002Fremotesensing\u002Fairchange_benchmark.html)|[TGRS2009](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F5169964)|Aerial Images|13|952x640|1.5m|-|\n\n\n## Multi-Modal and SAR Datasets\n\n|Year|Task|Target| Dataset |Publication|Source|Image Pairs |Image Size|Resolution|Location|Class|\n|:---|:---|:--- | :------| :------|:----------| :-------| :-------| :----------- | :----- | :---- |\n|2025|DDA|Disaster|[DisasterM3](https:\u002F\u002Fgithub.com\u002FJunjue-Wang\u002FDisasterM3)|[NeurIPS2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.21089)| Optical-SAR-Instruction |-|-|-|Global|-|\n|2025|SCD|Building| [BRIGHT](https:\u002F\u002Fgithub.com\u002FChenHongruixuan\u002FBRIGHT) | [arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.06019) |Optical and SAR|4,538| 1,024×1,024| 0.3-1m|Global|4|\n|2024|SCD|Building| [Hi-BCD](https:\u002F\u002Fgithub.com\u002FHATFormer\u002FMMCD) | [Information Fusion 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1566253524001362) |Aerial Images, DSMs|1,500| 1,000×1,000 |0.25m |Netherlands (Amsterdam, Rotterdam, and Utrecht)|3|\n|2024|SCD|Flood |[UrbanSARFloods](https:\u002F\u002Fgithub.com\u002Fjie666-6\u002FUrbanSARFloods)|[CVPR2024W](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2024W\u002FEarthVision\u002Fhtml\u002FZhao_UrbanSARFloods_Sentinel-1_SLC-Based_Benchmark_Dataset_for_Urban_and_Open-Area_Flood_CVPRW_2024_paper.html) | Sentinel-1|8,879| 512×512|20m|Global|5|\n|2024|SCD|Land use |[EVLab-CMCD](https:\u002F\u002Fgithub.com\u002Fwhudk\u002FEVLab-CMCD) | [ISPSR P&RS 2024](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271624003873)|GF-2, BJ-2, Historical land use maps|5,622|512×512| 0.8m| 10 Cities in China|13|\n|2023|BCD|Flood |[CAU-Flood](https:\u002F\u002Fgithub.com\u002FCAU-HE\u002FCMCDNet)| [JAG2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1569843223000195) |Sentinel-1, Sentinel-2|18,302| 256×256|10m|Global|2|\n|2023|SCD|Flood|[Kuro Siwo](https:\u002F\u002Fgithub.com\u002FOrion-AI-Lab\u002FKuroSiwo)|[NeurIPS2024](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2024\u002Fhash\u002F43612b0662cb6a4986edf859fd6ebafe-Abstract-Datasets_and_Benchmarks_Track.html)|Sentinel-1, DEM| 67,490 |224×224| 10m|Global|3|\n|2023|SCD|Urban|[SMARS](https:\u002F\u002Fwww.dlr.de\u002Fen\u002Feoc\u002Fabout-us\u002Fremote-sensing-technology-institute\u002Fphotogrammetry-and-image-analysis\u002Fpublic-datasets\u002Fsmars)| [ISPRS P&RS 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS092427162300254X)|Simulated Orthoimages and DSMs|-|512×512|0.3m, 0.5m|Simulated Paris and Venice|3|\n|2023|BCD|Urban|[3DCD](https:\u002F\u002Fsites.google.com\u002Funiroma1.it\u002F3dchangedetection\u002Fhome-page?pli=1) |[ISPRS P&RS 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271622003240)|Aerial Images, DSMs|472|400×400, 200×200|0.5m, 1m|Valladolid, Spain|2| \n|2023|SCD|Urban|[Urb3DCD–V2](https:\u002F\u002Fieee-dataport.org\u002Fopen-access\u002Furb3dcd-urban-point-clouds-simulated-dataset-3d-change-detection)|[ISPRS P&RS 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271623000394)|ALS, Multi-Sensor|-|-|-|Simulated|7|\n|2022|BCD|Flood| [Wuhan](https:\u002F\u002Fgithub.com\u002FGeoZcx\u002FA-Domain-Adaption-Neural-Network-for-Change-Detection-with-Heterogeneous-Optical-and-SAR-Remote-Sens\u002Ftree\u002Fmain\u002Fdata) | [JAG2022](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0303243422000952) |Sentinel-2, COSMO-SkyMed|1| 11,216×13,693|3m |Wuhan, China|2|\n|2022|BCD|Flood|[Ombria](https:\u002F\u002Fgithub.com\u002Fgeodrak\u002FOMBRIA) |[JSTARS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9723593\u002F) |Sentinel-1, Sentinel-2| 1,688| 256×256| 10m|Global|2|\n|2021|BCD|Land cover|[MultiModalOSCD](https:\u002F\u002Fgithub.com\u002FPatrickTUM\u002FmultimodalCD_ISPRS21)|[ISPRS. XXIV ISPRS Congress 2021](https:\u002F\u002Fisprs-archives.copernicus.org\u002Farticles\u002FXLIII-B3-2021\u002F243\u002F2021\u002Fisprs-archives-XLIII-B3-2021-243-2021.pdf)|Sentinel-1, Sentinel-2|24|600×600|10-60m|Global|2|\n\n# Tools\n\n| Year | Abbreviation | Description | Other|\n| :--- | :--- | :--- | :--- |\n|2024|[rschange](https:\u002F\u002Fgithub.com\u002Fxwmaxwma\u002Frschange)| An open-source toolbox dedicated to reproducing and developing advanced methods (e.g., DDLNet, CDMask) for change detection in remote sensing images.|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fxwmaxwma\u002Frschange.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fxwmaxwma\u002Frschange?style=social)|\n|2024|[torchange](https:\u002F\u002Fgithub.com\u002FZ-Zheng\u002Fpytorch-change-models)| A benchmark library providing out-of-box, straightforward implementations of contemporary spatiotemporal change detection models (e.g., ChangeStar, Changen, AnyChange), metrics, and datasets to promote reproducibility in remote sensing research. |![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZ-Zheng\u002Fpytorch-change-models.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-Zheng\u002Fpytorch-change-models?style=social)|\n|2022| [Open-CD](https:\u002F\u002Fgithub.com\u002Flikyoo\u002Fopen-cd)|The most comprehensive open-source toolbox for change detection, offering a unified platform with diverse methods, training\u002Finference tools, data analysis scripts, and benchmarks to support research and development in the field. Paper: [arXiv2024](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.15317). |![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flikyoo\u002Fopen-cd.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flikyoo\u002Fopen-cd?style=social)|\n|2022|[PaddleRS](https:\u002F\u002Fgithub.com\u002FPaddlePaddle\u002FPaddleRS)| A remote sensing toolkit based on PaddlePaddle that supports change detection among other tasks, providing dedicated models (e.g., BIT, FarSeg), large-image processing capabilities, and practical tutorials for analyzing temporal land cover differences. The PyTorch version is called [CDLab](https:\u002F\u002Fgithub.com\u002FBobholamovic\u002FCDLab).|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FPaddlePaddle\u002FPaddleRS.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FPaddlePaddle\u002FPaddleRS?style=social)|\n|2020|[Change Detection Repository](https:\u002F\u002Fgithub.com\u002FChenHongruixuan\u002FChangeDetectionRepository)|It provides Python implementations of selected traditional change detection methods (e.g., CVA, SFA, MAD) and deep learning-based approaches (e.g., SiamCRNN, DSFA, and FCN-based methods).|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FChenHongruixuan\u002FChangeDetectionRepository.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FChenHongruixuan\u002FChangeDetectionRepository?style=social)|\n|2019|[ChangeDetectionToolbox](https:\u002F\u002Fgithub.com\u002FBobholamovic\u002FChangeDetectionToolbox)|This MATLAB toolbox provides a modular, end-to-end framework for remote sensing change detection, implementing key methods such as CVA , MAD , and IRMAD to generate difference images and evaluate change maps.|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FBobholamovic\u002FChangeDetectionToolbox.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FBobholamovic\u002FChangeDetectionToolbox?style=social)|\n\n\n# Methods\n\n## Deep Learning\n\n### Foundation Models\n\n| Year | Abbreviation | Title | Publication |Foundation Models| Keywords | Experiment Datasets |Other|\n| :--- | :--- | :------| :--- | :--- | :--- |:------- |:------- |\n|2025|DaCDF|A change detection framework with relative depth information assistance|[JAG2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1569843225005898?dgcid=rss_sd_all)|Depth Anything|Depth-Anything; Multi-task learning|WHU-CD, LEVIR-CD, SECOND|-|\n|2025|[GeoVLM-R1](https:\u002F\u002Fgithub.com\u002Fmustansarfiaz\u002FGeoVLM-R1-Toolkit)|GeoVLM-R1: Reinforcement Fine-Tuning for Improved Remote Sensing Reasoning|[arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.25026)|Qwen2.5VL-3B-Instruct|Task aware rewards, reasoning based RL models|GeoChat-Instruct, NWPU VHR-10; Dubai-CC, LEVIR-MCI, MUDS, SYSU-CD; NWPU-Captions, RSCID-Captions, RSITMD-Captions|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fmustansarfiaz\u002FGeoVLM-R1-Toolkit.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmustansarfiaz\u002FGeoVLM-R1-Toolkit?style=social)|\n|2025|ChangeVG|Towards Comprehensive Interactive Change Understanding in Remote Sensing: A Large-scale Dataset and Dual-granularity Enhanced VLM|[arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.23105)|Qwen2.5-VL-7B|Remote sensing change understanding, Interactive multi-task instruction dataset, Vision-language models|ChangeIMTI (constructed from LEVIR-CC, LEVIR-MCI)|-|\n|2025|[SegChange-R1](https:\u002F\u002Fgithub.com\u002FYu-Zhouz\u002FSegChange-R1)|SegChange-R1: LLM-Augmented Remote Sensing Change Detection|[arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.17944)|Swin Transformer, Microsoft\u002FPhi-1.5|LLM-augmented inference approach, Linear attention-based spatial transformation module|WHU-CD, CDD, DSIFN-CD, DVCD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FYu-Zhouz\u002FSegChange-R1.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYu-Zhouz\u002FSegChange-R1?style=social)|\n|2025|[SAM2-CD](https:\u002F\u002Fgithub.com\u002FKimotaQY\u002FSAM2-CD)|SAM2-CD: Remote Sensing Image Change Detection With SAM2|[JSTAR2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11164661)|SAM2|Dynamic feature selection, global–local attention|WHU-CD, LEVIR-CD, and LEVIR-CD+|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FKimotaQY\u002FSAM2-CD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FKimotaQY\u002FSAM2-CD?style=social)|\n|2025|[ViTP](https:\u002F\u002Fgithub.com\u002Fzcablii\u002FViTP)|Visual Instruction Pretraining for Domain-Specific Foundation Models|[arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.17562)|ViT, InternVL-2.5|Leveraging reasoning to enhance perception, ViT, Visual Robustness Learning|16 challenging remote sensing and medical imaging benchmarks |![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fzcablii\u002FViTP.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzcablii\u002FViTP?style=social)|\n|2025|[AdaptVFMs-RSCD](https:\u002F\u002Fgithub.com\u002FJiang-CHD-YunNan\u002FRS-VFMs-Fine-tuning-Dataset)|AdaptVFMs-RSCD: Advancing Remote Sensing Change Detection from binary to semantic with SAM and CLIP|[ISPRS P&RS 2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271625003636?dgcid=rss_sd_all)|CLIP, SAM|Remote sensing VFM fine-tuning dataset|RS VFM Fine-tuning dataset, DSIFN-CD, CLCD, SYSU-CD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FJiang-CHD-YunNan\u002FRS-VFMs-Fine-tuning-Dataset.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJiang-CHD-YunNan\u002FRS-VFMs-Fine-tuning-Dataset?style=social)|\n|2025|[PeftCD](https:\u002F\u002Fgithub.com\u002Fdyzy41\u002FPeftCD)|PeftCD: Leveraging Vision Foundation Models with Parameter-Efficient Fine-Tuning for Remote Sensing Change Detection|[arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.09572)|SAM2, DINOv3|Vision Foundation Models, Parameter-Efficient Fine-Tuning|WHU-CD, CDD, LEVIR-CD, SYSU-CD, MSRSCD, MLCD, S2Looking|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fdyzy41\u002FPeftCD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdyzy41\u002FPeftCD?style=social)|\n|2025|DepthCD|Balanced Diffusion-Guided Fusion for Multimodal Remote Sensing Classification|[ISPRS P&RS 2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271625002072?dgcid=rss_sd_all)|ViT|Depth prompt, Dimensional correlation of change, Lightweight adapter, Binary change detection, Semantic change detection|SECOND,LandsatSCD, HiUCDs; SYSU-CD, HRCUS-CD, WRCD|-|\n|2025|[SA-CDNet](https:\u002F\u002Fgithub.com\u002FDREAMXFAR\u002FSA-CDNet)|Detect Changes Like Humans: Incorporating Semantic Priors for Improved Change Detection|[TGRS2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11159523)|FastSAM|Dual-stream decoder, multiscale feature, visual foundation model|AIRS, INRIA-Building, and WHU-Building; DLCCC, and LoveDA; WHU-CD, LEVIR-CD, LEVIR-CD+, S2Looking, WHU Cultivate Land Dataset |![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FDREAMXFAR\u002FSA-CDNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDREAMXFAR\u002FSA-CDNet?style=social)|\n| 2025 | [DynamicEarth](https:\u002F\u002Fgithub.com\u002Flikyoo\u002FDynamicEarth) | DynamicEarth: How Far are We from Open-Vocabulary Change Detection?  | [arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.12931)|SAM2, DINOv2|  Open-Vocabulary Change Detection| WHU-CD, LEVIR-CD, SECOND, S2Looking, and BANDON|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flikyoo\u002FDynamicEarth.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flikyoo\u002FDynamicEarth?style=social)|\n|2025|[DisasterM3](https:\u002F\u002Fgithub.com\u002FJunjue-Wang\u002FDisasterM3)| DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response | [NeurIPS2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.21089)|LLaVA, Kimi, InternVL, Qwen2.5, GeoCha, TeoChat, EarthDial, GPT4|Multi-hazard, Multi-sensor, Multi-task|DisasterM3|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FJunjue-Wang\u002FDisasterM3.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJunjue-Wang\u002FDisasterM3?style=social)|\n|2025|[EFI-SAM](https:\u002F\u002Fgithub.com\u002Fjuncyan\u002Fefi-sam)|SAM-Based Efficient Feature Integration Network for Remote Sensing Change Detection: A Case Study on Macao Sea Reclamation|[JSTARS2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11058393\u002F)|SAM|Random Fourier features, sea reclamation|CLCD, SYSU-CD, S2Looking, MLCD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fjuncyan\u002Fefi-sam.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjuncyan\u002Fefi-sam?style=social)|\n| 2024 | [AnyChange](https:\u002F\u002Fgithub.com\u002FZ-Zheng\u002Fpytorch-change-models\u002Fblob\u002Fmain\u002Ftorchange\u002Fmodels\u002Fsegment_any_change) |Segment Any Change | [NeurIPS2024](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2024\u002Ffile\u002F9415416201aa201902d1743c7e65787b-Paper-Conference.pdf) | SAM| Zero-shot change detection, bitemporal latent matching|xBD, LEVIR-CD, S2Looking, SECOND  | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZ-Zheng\u002Fpytorch-change-models.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-Zheng\u002Fpytorch-change-models?style=social) |\n|2024|[SCM](https:\u002F\u002Fgithub.com\u002FStephenApX\u002FUCD-SCM)|Segment Change Model (SCM) for Unsupervised Change detection in VHR Remote Sensing Images: a Case Study of Buildings|[IGARSS 2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10642429)|SAM, CLIP|Unsupervised Change Detection, Vision Foundation Model|WHU-CD, LEVIR-CD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FStephenApX\u002FUCD-SCM.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FStephenApX\u002FUCD-SCM?style=social) |\n|2024|[SemiCD-VL](https:\u002F\u002Fgithub.com\u002Flikyoo\u002FSemiCD-VL) |SemiCD-VL: Visual-Language Model Guidance Makes Better Semi-Supervised Change Detector| [TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10781418) |APE |Visual-language model, semi-supervised learning, foundation model|WHU-CD, LEVIR-CD| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flikyoo\u002FSemiCD-VL.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flikyoo\u002FSemiCD-VL?style=social) |\n|2024|[ChangeCLIP](https:\u002F\u002Fgithub.com\u002Fdyzy41\u002FChangeCLIP) | ChangeCLIP: Remote sensing change detection with multimodal vision-language representation learning | [ISPRS P&RS 2024](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271624000042) |CLIP| Multimodal, vision-Language Representation Learning |WHU-CD, CDD, LEVIR-CD, LEVIR-CD+, and SYSU-CD| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fdyzy41\u002FChangeCLIP.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdyzy41\u002FChangeCLIP?style=social) |\n| 2023 | [BAN](https:\u002F\u002Fgithub.com\u002Flikyoo\u002FBAN) | A New Learning Paradigm for Foundation Model-Based Remote-Sensing Change Detection | [TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F10438490\u002F) |CLIP| Foundation Model, visual tuning | WHU-CD, LEVIR-CD, S2Looking, Landsat-SCD, and BANDON| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flikyoo\u002FBAN.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flikyoo\u002FBAN?style=social) |\n| 2023 | [SAM-CD](https:\u002F\u002Fgithub.com\u002FggsDing\u002FSAM-CD) | Adapting Segment Anything Model for Change Detection in VHR Remote Sensing Images | [TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10443350)| SAM |Vision foundation models | WHU-CD, LEVIR-CD, CLCD, S2Looking| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FggsDing\u002FSAM-CD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FggsDing\u002FSAM-CD?style=social) |\n\n\n### Diffusion Models and GANs\n\n| Year | Abbreviation | Title | Publication | Keywords | Experiment Datasets |Other      |\n| :--- | :--- | :--- | :--- | :--- | :--- |:--- |\n|2025|[CT2Net](https:\u002F\u002Fgithub.com\u002FJiahuiqu\u002FCT2Net)|Cycle Translation-Based Collaborative Training for Hyperspectral-RGB Multimodal Change Detection|[TPAMI2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11164958)|CycleGAN, Hyperspectral-RGB image, multimodal change detection, image translation, collaborative training|Bay Area (HSI-RGB), Santa Barbara (HSI-RGB), Hermiston (HSI-RGB), XDU-Liyukou (HSI-RGB)|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FJiahuiqu\u002FCT2Net.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJiahuiqu\u002FCT2Net?style=social)|\n|2025|[NeDS](https:\u002F\u002Fgithub.com\u002FZ-Zheng\u002Fpytorch-change-models)|Neural disaster simulation for transferable building damage assessment|[RSE2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425725003839?dgcid=rss_sd_all)|Synthetic data fine-tuning, deep generative models, conditional latent diffusion model|xBD, Los Angeles Wildfire (2025), and Nigeria Flooding (2025)|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZ-Zheng\u002Fpytorch-change-models.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-Zheng\u002Fpytorch-change-models?style=social)|\n|2025|[BDGF](https:\u002F\u002Fgithub.com\u002FHaoLiu-XDU\u002FBDGF)|Balanced Diffusion-Guided Fusion for Multimodal Remote Sensing Classification|[arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.23310)|Denoising diffusion probabilistic models, adaptive modality masking strategy,mutual learning strategy|Berlin dataset (HSI+SAR), Augsburg dataset (HSI+SAR), Yellow River Estuary dataset (HSI+SAR), LCZ HK dataset (MSI+SAR)|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FHaoLiu-XDU\u002FBDGF.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHaoLiu-XDU\u002FBDGF?style=social)|\n|2025|[RS-NormGAN](https:\u002F\u002Fgithub.com\u002Flixinghua5540\u002FRS-NormGAN)|RS-NormGAN: Enhancing change detection of multi-temporal optical remote sensing images through effective radiometric normalization|ISPRS P&RS 2025|Deep style transfer; Domain adaptation; GAN; Multi-temporal radiometric normalization|GESD, SHCD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flixinghua5540\u002FRS-NormGAN.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flixinghua5540\u002FRS-NormGAN?style=social)|\n|2024|[UP-Diff](https:\u002F\u002Fgithub.com\u002Fzeyuwang-zju\u002FUP-Diff)|UP-Diff: Latent Diffusion Model for Remote Sensing Urban Prediction|[GRSL2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10807291)|Cross-attention, latent diffusion model, urban planning|LEVIR-CD, SYSU-CD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fzeyuwang-zju\u002FUP-Diff.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzeyuwang-zju\u002FUP-Diff?style=social)|\n|2024|[ChangeDiff](https:\u002F\u002Fgithub.com\u002FDZhaoXd\u002FChangeDiff)|ChangeDiff: A Multi-Temporal Change Detection Data Generator with Flexible Text Prompts via Diffusion Model|[AAAI2025](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F33058)|Diffusion models, text-to-layout model, multi-class distribution-guided text prompts|SECOND, Landsat-SCD, and HRSCD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FDZhaoXd\u002FChangeDiff.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDZhaoXd\u002FChangeDiff?style=social)|\n| 2024 | [Changen2](https:\u002F\u002Fgithub.com\u002FZ-Zheng\u002Fpytorch-change-models\u002Ftree\u002Fmain\u002Ftorchange\u002Fmodels\u002Fchangen2) | Changen2: Multi-Temporal Remote Sensing Generative Change Foundation Model | [TPAMI2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10713915\u002F) | Synthetic data pre-training, generative model, foundation model | WHU-CD, xBD, LEVIR-CD, S2Looking, SECOND| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZ-Zheng\u002Fpytorch-change-models.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-Zheng\u002Fpytorch-change-models?style=social) |\n| 2023 | [Changen](https:\u002F\u002Fgithub.com\u002FZ-Zheng\u002FChangen) | Scalable Multi-Temporal Remote Sensing Change Data Generation via Simulating Stochastic Change Process | [ICCV2023](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FICCV2023\u002Fpapers\u002FZheng_Scalable_Multi-Temporal_Remote_Sensing_Change_Data_Generation_via_Simulating_Stochastic_ICCV_2023_paper.pdf) | Deep generative model, change event simulation, semantic change synthesis | WHU-CD, LEVIR-CD, S2Looking| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZ-Zheng\u002FChangen.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-Zheng\u002FChangen?style=social) |\n| 2022 | [DDPM-CD](https:\u002F\u002Fgithub.com\u002Fwgcban\u002Fddpm-cd) | DDPM-CD: Denoising Diffusion Probabilistic Models as Feature Extractors for Remote Sensing Change Detection| [WACV2025](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FWACV2025\u002Fpapers\u002FBandara_DDPM-CD_Denoising_Diffusion_Probabilistic_Models_as_Feature_Extractors_for_Remote_WACV_2025_paper.pdf) | Image synthesis, Denoising Diffusion Probabilistic Models | WHU-CD, CDD, DSIFN-CD, and LEVIR-CD | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fwgcban\u002Fddpm-cd.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwgcban\u002Fddpm-cd?style=social) |\n\n\n### Transformers\n\n| Year | Abbreviation | Title | Publication | Keywords | Experiment Datasets |Other|\n| :--- | :--- | :--- | :--- | :--- | :--- |:--- |\n|2025|[BTC](https:\u002F\u002Fgithub.com\u002Fblaz-r\u002FBTC-change-detection)|Be the Change You Want to See: Revisiting Remote Sensing Change Detection Practices|[TGRS2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11063303)|Change detection, method optimization, remote sensing, supervised learning|SYSU-CD, LEVIR-CD, EGY-BCD, GVLM-CD, CLCD, OSCD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fblaz-r\u002FBTC-change-detection.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fblaz-r\u002FBTC-change-detection?style=social)|\n|2025|[CMNet](https:\u002F\u002Fgithub.com\u002FJscript10\u002FCMNet)|CMNet: A CNN–Mamba Network for Change Detection With Similarity Orientation and Difference Perception|[TGRS2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11208164\u002F)|Difference perception, similarity orientation, CNN–Mamba|DSIFN-CD, LEVIR-CD, SYSU-CD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FJscript10\u002FCMNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJscript10\u002FCMNet?style=social)|\n|2025|[MBUKG_DCKRL_CD](https:\u002F\u002Ffigshare.com\u002Farticles\u002Fonline_resource\u002FMBUKG_DCKRL_CD\u002F27897873)|An urban change detection method based on multimodal data and knowledge graph technology|[IJDE2025](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F17538947.2025.2564902?af=R)|Urban change detection, multimodal knowledge graph, multi-source data representation learning, dual cross-attention mechanism|A comprehensive dataset comprising VHR images, POI data, and SVI|-|\n|2025|[S-cCDNet](https:\u002F\u002Fgithub.com\u002FShelly-H\u002FS-cCDNet)|Semantic-centric change detection framework: considering spatiotemporal heterogeneity and spatiotemporal correlation of land cover|[IJDE2025](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F17538947.2025.2569406?af=R)|Multi-task learning, prototype representation, spatiotemporal heterogeneity, spatiotemporal correlation|SECOND, Landsat-SCD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FShelly-H\u002FS-cCDNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FShelly-H\u002FS-cCDNet?style=social)|\n|2025|[CPGNet](https:\u002F\u002Fgithub.com\u002Flong123524\u002FCPGNet)|Detecting semantic changes from VHR remote sensing images by integrating semantic correlations and change priors|[JAG2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1569843225005631?dgcid=rss_sd_all)|Semantic correlations; Multi-view; Change prior-guided network|JL1; Xiamen (XM) cropland non-agriculturalization dataset; SECOND|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flong123524\u002FCPGNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flong123524\u002FCPGNet?style=social)|\n|2025|[FoBa](https:\u002F\u002Fgithub.com\u002Fzmoka-zht\u002FFoBa)|FoBa: A Foreground-Background co-Guided Method and New Benchmark for Remote Sensing Semantic Change Detection|[arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.15788)| foreground background co-guided, bi-temporal interaction, mamba, new benchmark|SECOND, JL1, and the proposed LevirSCD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fzmoka-zht\u002FFoBa.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzmoka-zht\u002FFoBa?style=social)|\n|2025|[GSTM-SCD](https:\u002F\u002Fgithub.com\u002Fliuxuanguang\u002FGSTM-SCD)|GSTM-SCD: Graph-enhanced spatio-temporal state space model for semantic change detection in multi-temporal remote sensing images|[ISPRS P&RS 2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271625003557?dgcid=rss_sd_all)|State space model, Graph optimization, Spatio-temporal modeling|SECOND, Landsat-SCD, WUSU and DynamicEarthNet|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fliuxuanguang\u002FGSTM-SCD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fliuxuanguang\u002FGSTM-SCD?style=social)|\n|2025|[Change3D](https:\u002F\u002Fgithub.com\u002Fzhuduowang\u002FChange3D)|Change3D: Revisiting Change Detection and Captioning from A Video Modeling Perspective| [CVPR2025](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2025\u002Fhtml\u002FZhu_Change3D_Revisiting_Change_Detection_and_Captioning_from_A_Video_Modeling_CVPR_2025_paper.html)|Perception Feature Extraction, Change Decoder, Caption Decoder|WHU-CD, HRSCD, xBD, LEVIR-CD, CLCD, SECOND, LEVIR-CC, and DUBAI-CC|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fzhuduowang\u002FChange3D.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhuduowang\u002FChange3D?style=social)|\n| 2025 |[UA-BCD](https:\u002F\u002Fgithub.com\u002FHenryjiepanli\u002FUA-BCD)| Overcoming the uncertainty challenges in detecting building changes from remote sensing images | [ISPRS P&RS 2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS092427162400426X) | Uncertainty-related theory, Building change detection mapping, Siamese pyramid vision transformer|CDD, WHU-CD, GZ-CD, LEVIR-CD, SYSU-CD| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FHenryjiepanli\u002FUA-BCD.svg?style=flat&logo=github&label=Last%20Commit) ![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHenryjiepanli\u002FUA-BCD?style=social)|\n|2025|[SMGNet](https:\u002F\u002Fgithub.com\u002Flong123524\u002FSMGNet)|SMGNet: A Semantic Map-Guided Multitask Neural Network for Remote Sensing Image Semantic Change Detection|[GRSL2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11023838)|Historical semantic information, pseudochanges, semantic map-guided network, underdetection|HRSCD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flong123524\u002FSMGNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flong123524\u002FSMGNet?style=social)|\n|2024|[HGINet](https:\u002F\u002Fgithub.com\u002Flong123524\u002FHGINet-torch)|Semantic change detection using a hierarchical semantic graph interaction network from high-resolution remote sensing images|[ISPRS P&RS 2024](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271624001709)|Hierarchical semantic graph interaction network; Temporal correlations; Semantic difference interaction|SECOND, HRSCD, Fuzhou, and Xiamen|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flong123524\u002FHGINet-torch.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flong123524\u002FHGINet-torch?style=social)|\n| 2024 |STCA| Towards transferable building damage assessment via unsupervised single-temporal change adaptation | [RSE2024](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425724004425?dgcid=rss_sd_all) | Unsupervised adaptation, single-temporal learning, semantic change detection | xBD, Turkey–Syria earthquake (2023), Kalehe DRC flooding (2023), Maui Hawaii fire (2023) | - |\n| 2024 | [ChangeSparse](https:\u002F\u002Fgithub.com\u002FZ-Zheng\u002Fpytorch-change-models\u002Fblob\u002Fmain\u002Ftorchange\u002Fmodels\u002Fchangesparse.py) | Unifying Remote Sensing Change Detection via Deep Probabilistic Change Models: from Principles, Models to Applications | [ISPRS P&RS 2024](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271624002624) | Probabilistic change model, sparsity of change, sparse change transformer | CDD, S2Looking, California Flood dataset, xBD, SECOND, DynamicEarthNet | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZ-Zheng\u002Fpytorch-change-models.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-Zheng\u002Fpytorch-change-models?style=social) |\n| 2024 | [ChangeStar2](https:\u002F\u002Fgithub.com\u002FZ-Zheng\u002Fpytorch-change-models\u002Fblob\u002Fmain\u002Ftorchange\u002Fmodels\u002Fchangestar2.py) | Single-Temporal Supervised Learning for Universal Remote Sensing Change Detection | [IJCV2024](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs11263-024-02141-4) | Universal change detection, single-temporal supervised learning |WHU-CD, CDD, xBD, LEVIR-CD, S2Looking, SpaceNet8, DynamicEarthNet, SECOND| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZ-Zheng\u002Fpytorch-change-models.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-Zheng\u002Fpytorch-change-models?style=social) |\n| 2024 | [BiFA](https:\u002F\u002Fgithub.com\u002Fzmoka-zht\u002FBiFA) | BiFA: Remote Sensing Image Change Detection With Bitemporal Feature Alignment | [TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10471555) | Bitemporal interaction, feature alignment, flow field|WHU-CD, LEVIR-CD, LEVIR-CD+, SYSU-CD, DSIFN-CD, and CLCD| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fzmoka-zht\u002FBiFA.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzmoka-zht\u002FBiFA?style=social)|\n| 2024 | [CDMamba](https:\u002F\u002Fgithub.com\u002Fzmoka-zht\u002FCDMamba) | CDMamba: Incorporating Local Clues Into Mamba for Remote Sensing Image Binary Change Detection | [TGRS2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10902569) | Mamba, bitemporal interaction, state space model|WHU-CD, CDD, LEVIR-CD, LEVIR-CD+, and CLCD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fzmoka-zht\u002FCDMamba.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzmoka-zht\u002FCDMamba?style=social) |\n| 2024 | [CDMask](https:\u002F\u002Fgithub.com\u002Fxwmaxwma\u002Frschange) | Rethinking Remote Sensing Change Detection With A Mask View | [arXiv2024](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.15320) |Mask view, mask-level Classification, MaskFormer|WHU-CD, LEVIR-CD, SYSU-CD, DSIFN-CD, and CLCD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fxwmaxwma\u002Frschange.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fxwmaxwma\u002Frschange?style=social)|\n| 2024 | [ChangeMamba](https:\u002F\u002Fgithub.com\u002FChenHongruixuan\u002FChangeMamba) | ChangeMamba: Remote Sensing Change Detection With Spatiotemporal State Space Model | [TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10565926) | Mamba, spatiotemporal relationship, state space model|WHU-CD, xBD, SECOND, LEVIR-CD+, and SYSU-CD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FChenHongruixuan\u002FChangeMamba.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FChenHongruixuan\u002FChangeMamba?style=social) |\n| 2024 | [MaskCD](https:\u002F\u002Fgithub.com\u002FAI4RS\u002FMaskCD) | MaskCD: A Remote Sensing Change Detection Network Based on Mask Classification | [TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10587034) | Deformable attention, mask classification, masked cross-attention|LEVIR-CD, CLCD, SYSU-CD, EGY-BCD, and GVLM-CD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FAI4RS\u002FMaskCD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAI4RS\u002FMaskCD?style=social) |\n| 2024 | [M-CD](https:\u002F\u002Fgithub.com\u002FJayParanjape\u002FM-CD) | A Mamba-based Siamese Network for Remote Sensing Change Detection | [arXiv2024](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.06839) | Mamba, state space model, difference Module| WHU-CD, CDD, DSIFN-CD, and LEVIR-CD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FJayParanjape\u002FM-CD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJayParanjape\u002FM-CD?style=social) |\n| 2024 | [ScratchFormer](https:\u002F\u002Fgithub.com\u002Fmustansarfiaz\u002FScratchFormer) | Remote Sensing Change Detection With Transformers Trained From Scratch | [TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10489990) | Trained from scratch, shuffled sparse-attention operation, change-enhanced feature fusion, | WHU-CD, OSCD, CDD, DSIFN-CD, and LEVIR-CD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fmustansarfiaz\u002FScratchFormer.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmustansarfiaz\u002FScratchFormer?style=social) |\n| 2024 | [SitsSCD](https:\u002F\u002Fgithub.com\u002FElliotVincent\u002FSitsSCD) |Satellite Image Time Series Semantic Change Detection: Novel Architecture and Analysis of Domain Shift| [arXiv2024](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.07616)| Temporal attention, Temporal shift, Spatial shift| DynamicEarthNet, MUDS|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FElliotVincent\u002FSitsSCD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FElliotVincent\u002FSitsSCD?style=social) |\n| 2023 | [3DCD](https:\u002F\u002Fgithub.com\u002FVMarsocci\u002F3DCD) | Inferring 3D change detection from bitemporal optical images | [ISPRS P&RS 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271622003240) | 3D Change Detection, Elevation change detection | 3DCD | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FVMarsocci\u002F3DCD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FVMarsocci\u002F3DCD?style=social) |\n| 2023 | [Siamese KPConv](https:\u002F\u002Fgithub.com\u002FIdeGelis\u002Ftorch-points3d-SiameseKPConv) | Siamese KPConv: 3D multiple change detection from raw point clouds using deep learning | [ISPRS P&RS 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271623000394?via%3Dihub) | 3D Change Detection, Siamese network, 3D Kernel Point Convolution | Urb3DCD–V2, AHN-CD, Change3D | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FIdeGelis\u002Ftorch-points3d-SiameseKPConv.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FIdeGelis\u002Ftorch-points3d-SiameseKPConv?style=social) |\n| 2023 | [MapFormer](https:\u002F\u002Fgithub.com\u002Fmxbh\u002Fmapformer) | MapFormer: Boosting Change Detection by Using Pre-change Information | [ICCV2023](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FICCV2023\u002Fpapers\u002FBernhard_MapFormer_Boosting_Change_Detection_by_Using_Pre-change_Information_ICCV_2023_paper.pdf) | Conditional Change Detection, multi-modal feature fusion, cross-modal contrastive loss|HRSCD, DynamicEarthNet   | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fmxbh\u002Fmapformer.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmxbh\u002Fmapformer?style=social) |\n| 2023 | [CACo](https:\u002F\u002Fgithub.com\u002Futkarshmall13\u002Fcaco) | Change-Aware Sampling and Contrastive Learning for Satellite Images | [CVPR2023](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2023\u002Fpapers\u002FMall_Change-Aware_Sampling_and_Contrastive_Learning_for_Satellite_Images_CVPR_2023_paper.pdf) | Self-supervised learning, Change-Aware Contrastive Loss| OSCD, DynamicEarthNet, EuroSat, and BigEarthNet| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Futkarshmall13\u002Fcaco.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Futkarshmall13\u002Fcaco?style=social) |\n| 2023 | [Self-Pair](https:\u002F\u002Fgithub.com\u002Fseominseok0429\u002FSelf-Pair-for-Change-Detection) | Self-Pair: Synthesizing Changes from Single Source for Object Change Detection in Remote Sensing Imagery | [WACV2023](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FWACV2023\u002Fpapers\u002FSeo_Self-Pair_Synthesizing_Changes_From_Single_Source_for_Object_Change_Detection_WACV_2023_paper.pdf) | Synthetic data, single-temporal supervision, visual similarity in unchanged area | WHU-CD, SpaceNet2, xBD, LEVIR-CD | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fseominseok0429\u002FSelf-Pair-for-Change-Detection.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fseominseok0429\u002FSelf-Pair-for-Change-Detection?style=social) |\n| 2022 | [Changer](https:\u002F\u002Fgithub.com\u002Flikyoo\u002Fopen-cd\u002Ftree\u002Fmain\u002Fconfigs\u002Fchanger) | Changer: Feature Interaction is What You Need for Change Detection | [TGRS2023](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10129139) | Feature Interaction | LEVIR-CD, S2Looking | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flikyoo\u002Fopen-cd.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flikyoo\u002Fopen-cd?style=social) |\n| 2022 | [ChangeMask](https:\u002F\u002Fgithub.com\u002FZ-Zheng\u002Fpytorch-change-models\u002Fblob\u002Fmain\u002Ftorchange\u002Fmodels\u002Fchangemask.py) | ChangeMask: Deep Multi-task Encoder-Transformer-Decoder Architecture for Semantic Change Detection | [ISPRS P&RS 2022](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271621002835) | Multi-task learning, temporal symmetry, multi-temporal|SECOND, Hi-UCD| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZ-Zheng\u002Fpytorch-change-models.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-Zheng\u002Fpytorch-change-models?style=social) |\n| 2022 | [FHD](https:\u002F\u002Fgithub.com\u002FZSVOS\u002FFHD) | Feature Hierarchical Differentiation for Remote Sensing Image Change Detection | [GRSL2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9837915) | Hierarchical differentiation, time-specific features| DSIFN, LEVIR-CD, LEVIR-CD+, S2Looking | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZSVOS\u002FFHD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZSVOS\u002FFHD?style=social) |\n| 2022 | [SST-Former](https:\u002F\u002Fgithub.com\u002Fyanhengwang-heu\u002FIEEE_TGRS_SSTFormer) | Spectral–spatial–temporal transformers for hyperspectral image change detection | [TGRS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9870837) | Hyperspectral, cross-attention, self-attention |Farmland CD dataset, Barbara CD dataset, and Bay Area CD dataset  | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fyanhengwang-heu\u002FIEEE_TGRS_SSTFormer.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyanhengwang-heu\u002FIEEE_TGRS_SSTFormer?style=social) |\n| 2022 | [CDViT](https:\u002F\u002Fgithub.com\u002Fshinianzhihou\u002FChangeDetection) | A Divided Spatial and Temporal Context Network for Remote Sensing Change Detection | [JSTARS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9779962) | Self-attention, spatial-temporal transformer | WHU-CD, LEVIR-CD | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fshinianzhihou\u002FChangeDetection.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fshinianzhihou\u002FChangeDetection?style=social) |\n| 2022 | [ChangeFormer](https:\u002F\u002Fgithub.com\u002Fwgcban\u002FChangeFormer) | A Transformer-Based Siamese Network for Change Detection | [IGARSS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9883686) | Transformer Siamese network, attention mechanism| DSIFN-CD, and LEVIR-CD| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fwgcban\u002FChangeFormer.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwgcban\u002FChangeFormer?style=social) |\n| 2021 | [BIT](https:\u002F\u002Fgithub.com\u002Fjustchenhao\u002FBIT_CD) | Remote Sensing Image Change Detection with Transformers | [TGRS2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9491802) | Transformer | WHU-CD, DSIFN-CD, LEVIR-CD | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fjustchenhao\u002FBIT_CD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjustchenhao\u002FBIT_CD?style=social) |\n\n\n### CNNs\n\n| Year | Abbreviation | Title | Publication | Keywords | Experiment Datasets |Other|\n| :--- | :--- | :--- | :--- | :--- | :--- |:--- |\n|2025|[RACDNet](https:\u002F\u002Fgithub.com\u002FLYT-max\u002FRACDNet)|Towards resolution-arbitrary remote sensing change detection with Spatial-frequency dual domain learning|[ISPRS P&RS 2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271625004113?dgcid=rss_sd_all)|Resolution-arbitrary change detection; Gradient prior; Dual-domain learning|WHU-CD, LEVIR-CD, SYSU-CD, and Google dataset|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FLYT-max\u002FRACDNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLYT-max\u002FRACDNet?style=social)|\n|2025|[RIEM](https:\u002F\u002Fgithub.com\u002Fyulisun\u002FRIEM)|Detecting changes without comparing images: Rules induced change detection in heterogeneous remote sensing images|[ISPRS P&RS 2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271625003612?dgcid=rss_sd_all)|Heterogeneous data, Multimodal, Energy based model|Multi-source data|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fyulisun\u002FRIEM.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyulisun\u002FRIEM?style=social)|\n|2025|[Semantic-TemporalNet](https:\u002F\u002Fgithub.com\u002FCUG-BEODL\u002FSTN)|Semantic-TemporalNet: A Novel Urban Block Change Detection Method Based on Semantic Coherence Analysis|[TGRS2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11172373)|Sentinel-2, time-series semantic coherence, urban renewal|Changsha and Wuhan Sentinel-2 imagery|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FCUG-BEODL\u002FSTN.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FCUG-BEODL\u002FSTN?style=social)|\n|2025|[TripleS](https:\u002F\u002Fgithub.com\u002FStephenApX\u002FMTL-TripleS)|TripleS: Mitigating multi-task learning conflicts for semantic change detection in high-resolution remote sensing imagery|[ISPRS P&RS 2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271625003776?dgcid=rss_sd_all)|Multi-task learning, Land-cover and land-use|HRSCD, SC-SCD7, CC-SCD5|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FStephenApX\u002FMTL-TripleS.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FStephenApX\u002FMTL-TripleS?style=social)|\n| 2025 | CDFNet | Cross-scenario damaged building extraction network: Methodology, application, and efficiency using single-temporal HRRS imagery | [ISPRS P&RS2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271625002540?dgcid=rss_sd_all) | Building damage extraction, cross-scenario, single-temporal, feature decomposition | Post-disaster damaged building datasets of Yunnan and Harvey,  An auxiliary dataset (two earthquake-prone, one flood-prone, four non-disaster areas),  An application testing dataset (eight heterogeneous regions spanning volcano, earthquake, tsunami, wildfire, and hurricane scenarios) |-|\n|2025|[PRO-HRSCD](https:\u002F\u002Fgithub.com\u002Fsdust-mmlab\u002FPRO-HRSCD)|Rethinking Semantic Change Detection From a Semantic Alignment Perspective|[TGRS2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11162709\u002F)|Feature space alignment, multitask learning, prototype learning|SECOND, and Landsat-SCD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fsdust-mmlab\u002FPRO-HRSCD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsdust-mmlab\u002FPRO-HRSCD?style=social)|\n|2025|H-FIENet|Flood inundation monitoring using multi-source satellite imagery: a knowledge transfer strategy for heterogeneous image change detection|[RSE2024](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425724003997)|Flood mapping, Multi-source images, Cross-task transform|Gaofen-2, Gaofen-3, Sentinel-1, and Sentinel-2|-|\n|2024|[STMNet](https:\u002F\u002Fgithub.com\u002FZhoutya\u002FChangeDetection-STMNet)|STMNet: Single-Temporal Mask-Based Network for Self-Supervised Hyperspectral Change Detection|[TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10817647)|hyperspectral image, multiscale feature, single temporal, mask|Farmland dataset, Hermiston dataset, Bay dataset|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZhoutya\u002FChangeDetection-STMNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZhoutya\u002FChangeDetection-STMNet?style=social)|\n|2024|[ClearSCD](https:\u002F\u002Fgithub.com\u002Ftangkai-RS\u002FClearSCD)|The ClearSCD model: Comprehensively leveraging semantics and change relationships for semantic change detection in high spatial resolution remote sensing imagery|[ISPRS P&RS 2024](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271624001734)|Multi-task learning, contrastive learning, change vector analysis|Hi-UCD, LsSCD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Ftangkai-RS\u002FClearSCD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftangkai-RS\u002FClearSCD?style=social) |\n| 2024 | [SSLChange](https:\u002F\u002Fgithub.com\u002FMarsZhaoYT\u002FSSLChange)| SSLChange: A Self-Supervised Change Detection Framework Based on Domain Adaptation| [TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10741199)| Domain adaption, hierarchical features, image contrastive learning|CDD, LEVIR-CD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FMarsZhaoYT\u002FSSLChange.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FMarsZhaoYT\u002FSSLChange?style=social) |\n|2024|[U-Net, U-Net SiamDiff, and U-Net SiamConc](https:\u002F\u002Fgithub.com\u002Fisaaccorley\u002Fa-change-detection-reality-check) | A Change Detection Reality Check | [ICLR2024W](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.06994) | Reality Check, Benchmarking |WHU-CD, LEVIR-CD| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fisaaccorley\u002Fa-change-detection-reality-check.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fisaaccorley\u002Fa-change-detection-reality-check?style=social) |\n|2024|CCNet| Harmony in diversity: Content cleansing change detection framework for very-high-resolution remote-sensing images|[ISPRS P&RS 2024](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS092427162400340X)|Feature disentanglement, Content cleansing, Image restoration|CDD, LEVIR-CD, xBD, SECOND, SYSU-CD, Multi-temporal xBD|-|\n| 2023 | [I3PE](https:\u002F\u002Fgithub.com\u002FChenHongruixuan\u002FI3PE) | Exchange means change: An unsupervised single-temporal change detection framework based on intra-and inter-image patch exchange | [ISPRS P&RS 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS092427162300309X) | Single-temporal change detection, image patch exchange, adaptive clustering | SYSU-CD, SECOND, Wuhan dataset| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FChenHongruixuan\u002FI3PE.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FChenHongruixuan\u002FI3PE?style=social) |\n| 2023 | [A2Net](https:\u002F\u002Fgithub.com\u002Fguanyuezhen\u002FA2Net) | Lightweight Remote Sensing Change Detection With Progressive Feature Aggregation and Supervised Attention | [TGRS2023](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10034814) | Lightweight, progressive feature aggregation, supervised Attention |WHU-CD, LEVIR-CD and SYSU-CD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fguanyuezhen\u002FA2Net.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fguanyuezhen\u002FA2Net?style=social) |\n| 2023 | [DMINet](https:\u002F\u002Fgithub.com\u002FZhengJianwei2\u002FDMINet) | Change Detection on Remote Sensing Images Using Dual-Branch Multilevel Intertemporal Network | [TGRS2023](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10034787) | Dual-branch difference acquisition, intertemporal joint-attention, multilevel aggregation|WHU-CD, GZ-CD, LEVIR-CD, and SYSU-CD|![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZhengJianwei2\u002FDMINet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZhengJianwei2\u002FDMINet?style=social) |\n| 2023 | [AFCF3D-Net](https:\u002F\u002Fgithub.com\u002Fwm-Githuber\u002FAFCF3D-Net) | Adjacent-level feature cross-fusion with 3D CNN for remote sensing image change detection | [TGRS2023](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10221754) | 3D CNN, feature cross-fusion, full-scale connection|WHU-CD, LEVIR-CD, SYSU-CD| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fwm-Githuber\u002FAFCF3D-Net.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwm-Githuber\u002FAFCF3D-Net?style=social) |\n| 2023 | [LightCDNet](https:\u002F\u002Fgithub.com\u002FNightSongs\u002FLightCDNet) | LightCDNet: Lightweight Change Detection Network Based on VHR Images | [GRSL2023](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10214556) | Early fusion, lightweight, deep supervised fusion|LEVIR-CD| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FNightSongs\u002FLightCDNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FNightSongs\u002FLightCDNet?style=social) |\n| 2023 | [USSFC-Net](https:\u002F\u002Fgithub.com\u002FSUST-reynole\u002FUSSFC-Net) | Ultralightweight Spatial–Spectral Feature Cooperation Network for Change Detection in Remote Sensing Images | [TGRS2023](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10081023) | Ultralightweight, multiscale feature extraction, spatial–spectral feature cooperation| CDD, DSIFN-CD, LEVIR-CD | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FSUST-reynole\u002FUSSFC-Net.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSUST-reynole\u002FUSSFC-Net?style=social) |\n| 2023 | [SAR-CD](https:\u002F\u002Fgithub.com\u002Fjanne-alatalo\u002Fsar-change-detection) | Improved Difference Images for Change Detection Classifiers in SAR Imagery Using Deep Learning | [TGRS2023](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10286479) |Mapping transformation function, SAR, U-Net| SCDD | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fjanne-alatalo\u002Fsar-change-detection.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjanne-alatalo\u002Fsar-change-detection?style=social) |\n| 2022 | [RDPNet](https:\u002F\u002Fgithub.com\u002FChnja\u002FRDPNet) | RDP-Net: Region detail preserving network for change detection | [TGRS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9970750) | Training strategy, edge loss, lightweight backbone | CDD,LEVIR-CD | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FChnja\u002FRDPNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FChnja\u002FRDPNet?style=social) |\n| 2022 | [FFCTL](https:\u002F\u002Fgithub.com\u002Flauraset\u002FFFCTL) | A full-level fused cross-task transfer learning method for building change detection using noise-robust pretrained networks on crowdsourced labels | [RSE2022](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425722004771) | Transfer learning, crowdsourced label,pseudo label |ZY-3 building and change detection dataset  | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flauraset\u002FFFCTL.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flauraset\u002FFFCTL?style=social) |\n| 2022 | [SaDL_CD](https:\u002F\u002Fgithub.com\u002Fjustchenhao\u002FSaDL_CD) | Semantic-aware Dense Representation Learning for Remote Sensing Image Change Detection | [TGRS2022](https:\u002F\u002Fgithub.com\u002Fjustchenhao\u002FSaDL_CD) | Self-supervised learning, semantic-aware representation learning| WHU-CD, GZ-CD, LEVIR-CD | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fjustchenhao\u002FSaDL_CD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjustchenhao\u002FSaDL_CD?style=social) |\n| 2022 | [TinyCD](https:\u002F\u002Fgithub.com\u002FAndreaCodegoni\u002FTiny_model_4_CD) | TINYCD: A (Not So) Deep Learning Model For Change Detection | [Neural Comput & Applic 2022](https:\u002F\u002Fgithub.com\u002FAndreaCodegoni\u002FTiny_model_4_CD) | Lightweight, tiny Model, siamese U-Net architecture, feature interaction | WHU-CD, LEVIR-CD | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FAndreaCodegoni\u002FTiny_model_4_CD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAndreaCodegoni\u002FTiny_model_4_CD?style=social) |\n| 2022 | [SDACD](https:\u002F\u002Fgithub.com\u002FPerfect-You\u002FSDACD) | An End-to-end Supervised Domain Adaptation Framework for Cross-Domain Change Detection | [PR2022](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS003132032200440X) | Supervised Domain Adaptation, Image Adaptation, Feature Adaptation |CDD, and WHU-CD | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FPerfect-You\u002FSDACD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FPerfect-You\u002FSDACD?style=social) |\n| 2022 | [Bi-SRNet](https:\u002F\u002Fgithub.com\u002FggsDing\u002FBi-SRNet) | Bi-temporal semantic reasoning for the semantic change detection in HR remote sensing images | [TGRS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9721305) | Triple-branch, semantic correlations| SECOND| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FggsDing\u002FBi-SRNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FggsDing\u002FBi-SRNet?style=social) |\n| 2022 | [SemiCD](https:\u002F\u002Fgithub.com\u002Fwgcban\u002FSemiCD) | Revisiting Consistency Regularization for Semi-supervised Change Detection in Remote Sensing Images | [arXiv2022](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.08454) | Semi-supervised, Consistency Regularization | WHU-CD, LEVIR-CD | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fwgcban\u002FSemiCD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwgcban\u002FSemiCD?style=social) |\n| 2022 | [FCCDN](https:\u002F\u002Fgithub.com\u002Fchenpan0615\u002FFCCDN_pytorch) | FCCDN: Feature Constraint Network for VHR Image Change Detection | [ISPRS P&RS 2022](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271622000636) | Self-supervised learning, non-local feature pyramid network, dual encoder-decoder backbone|WHU-CD, LEVIR-CD, SECOND| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fchenpan0615\u002FFCCDN_pytorch.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchenpan0615\u002FFCCDN_pytorch?style=social) |\n| 2021 | [ChangeStar](https:\u002F\u002Fgithub.com\u002FZ-Zheng\u002FChangeStar) | Change is Everywhere: Single-Temporal Supervised Object Change Detection in Remote Sensing Imagery | [ICCV2021](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FICCV2021\u002Fpapers\u002FZheng_Change_Is_Everywhere_Single-Temporal_Supervised_Object_Change_Detection_in_Remote_ICCV_2021_paper.pdf) | Single-temporal supervision, temporal symmetry| xBD, SpaceNet2, WHU-CD, LEVIR-CD| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZ-Zheng\u002FChangeStar.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-Zheng\u002FChangeStar?style=social) |\n| 2021 | [ChangeOS](https:\u002F\u002Fgithub.com\u002FZ-Zheng\u002FChangeOS) | Building damage assessment for rapid disaster response with a deep object-based semantic change detection framework: from natural disasters to man-made disasters | [RSE2021](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425721003564) |Semantic change detection, disaster response, OBIA| xBD, The Beirut port explosion (2020), The Bata military barracks explosion (2021) | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZ-Zheng\u002FChangeOS.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-Zheng\u002FChangeOS?style=social) |\n| 2021 | [Optical-SAR-CD](https:\u002F\u002Fgitlab.lrz.de\u002Fai4eo\u002Fcd\u002F-\u002Ftree\u002Fmain\u002FsarOpticalMultisensorTgrs2021) | Self-supervised multisensor change detection | [TGRS2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9538396) | Self-supervised, Multisensor | OSCD (Sentinel-2 and Sentinel-1) | - |\n| 2021 | [CEECNet](https:\u002F\u002Fgithub.com\u002Ffeevos\u002Fceecnet) | Looking for change? Roll the Dice and demand Attention | [RS2021](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F13\u002F18\u002F3707) | Dice similarity, attention module | WHU-CD, LEVIR-CD | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Ffeevos\u002Fceecnet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ffeevos\u002Fceecnet?style=social) |\n| 2021 | [ESCNet](https:\u002F\u002Fgithub.com\u002FBobholamovic\u002FESCNet) | ESCNet: An End-to-End Superpixel-Enhanced Change Detection Network for Very-High-Resolution Remote Sensing Images | [TNNLS2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9474911) | Superpixel segmentation, adaptive superpixel merging | SZTAKI, CDD| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FBobholamovic\u002FESCNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FBobholamovic\u002FESCNet?style=social) |\n| 2021 | [SeCo](https:\u002F\u002Fgithub.com\u002FElementAI\u002Fseasonal-contrast) | Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data | [ICCV2021](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FICCV2021\u002Fhtml\u002FManas_Seasonal_Contrast_Unsupervised_Pre-Training_From_Uncurated_Remote_Sensing_Data_ICCV_2021_paper.html) | Self-supervised learning| BigEarthNet, EuroSAT, OSCD | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FElementAI\u002Fseasonal-contrast.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FElementAI\u002Fseasonal-contrast?style=social) |\n| 2021 | [SRCDNet](https:\u002F\u002Fgithub.com\u002Fliumency\u002FSRCDNet) | Super-resolution-based Change Detection Network with Stacked Attention Module for Images with Different Resolutions | [TGRS2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9472869) | Super-resolution, metric learning | BCDD, CDD, GZ-CD | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fliumency\u002FSRCDNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fliumency\u002FSRCDNet?style=social) |\n| 2021 | [IAug-CDNet](https:\u002F\u002Fgithub.com\u002Fjustchenhao\u002FIAug_CDNet) | Adversarial Instance Augmentation for Building Change Detection in Remote Sensing Images | [TGRS2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9386248) | Adversarial instance augmentation, synthetic data| WHU-CD, LEVIR-CD | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fjustchenhao\u002FIAug_CDNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjustchenhao\u002FIAug_CDNet?style=social) |\n| 2021 | [SNUNet-CD](https:\u002F\u002Fgithub.com\u002Flikyoo\u002Fopen-cd\u002F) | SNUNet-CD: A Densely Connected Siamese Network for Change Detection of VHR Images | [GRSL2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9355573) | Fully convolutional siamese network | CDD | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flikyoo\u002Fopen-cd.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flikyoo\u002Fopen-cd?style=social) |\n| 2021 | [DDNet](https:\u002F\u002Fgithub.com\u002Fsummitgao\u002FSAR_CD_DDNet) | Change Detection in Synthetic Aperture Radar Images Using a Dual-Domain Network | [GRSL2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9420150) | SAR, frequency domain | Ottawa dataset, Sulzberger dataset, Yellow River dataset| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fsummitgao\u002FSAR_CD_DDNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsummitgao\u002FSAR_CD_DDNet?style=social) |\n| 2021 | [ACDA](https:\u002F\u002Fgithub.com\u002Fmeiqihu\u002FACDA) | Hyperspectral anomaly change detection based on autoencoder | [JSTARS2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9380336) | Hyperspectral, Anomaly Change Detection, Autoencoder | Viareggio 2013| ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fmeiqihu\u002FACDA.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmeiqihu\u002FACDA?style=social) |\n| 2018 | [FC-EF, FC-Siam-diff, FC-Siam-conc](https:\u002F\u002Fgithub.com\u002Frcdaudt\u002Ffully_convolutional_change_detection) | Fully convolutional siamese networks for change detection | [ICIP2018](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8451652) | Fully Convolutional Siamese Networks | SZTAKI, OSCD | ![Last Commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Frcdaudt\u002Ffully_convolutional_change_detection.svg?style=flat&logo=github&label=Last%20Commit)![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Frcdaudt\u002Ffully_convolutional_change_detection?style=social) |\n\n\n## Traditional Methods\n\n| Year | Abbreviation | Title | Publication | Keywords | Experiment Datasets |\n| :--- | :--- | :--- | :--- | :--- | :--- |\n|2025|[PWTT](https:\u002F\u002Fgithub.com\u002Foballinger\u002FPWTT)|Open access battle damage detection via Pixel-Wise T-Test on Sentinel-1 imagery|[RSE2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425725004298?dgcid=rss_sd_all)|Probabilistic change detection; Building damage assessment; Armed conflict|[UNOSAT damage annotation dataset](https:\u002F\u002Fgithub.com\u002Foballinger\u002FPWTT)|\n|2021|[SiROC](https:\u002F\u002Fgithub.com\u002Flukaskondmann\u002FSiROC)|Spatial Context Awareness for Unsupervised Change Detection in Optical Satellite Images|[TGRS2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9627707)|Multitemporal, optical images, unsupervised, urban analysis|OSCD, Beirut Harbor Explosion Dataset, Agriculture Dataset, Alpine Dataset|\n|2015|[CCDC](https:\u002F\u002Fgithub.com\u002FGERSL\u002FCCDC)|Generating synthetic Landsat images based on all available Landsat data: Predicting Landsat surface reflectance at any given time|[RSE2015](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425715000590)|Synthetic, Landsat, Surface reflectance, Time series model| Six Landsat scenes at different places in the Conterminous United States|\n|2013|SFA|Slow Feature Analysis for Change Detection in Multispectral Imagery|[TGRS2013](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F6553145)|Image transformation, slow feature analysis|Taizhou City ETM Data Set, Kunshan City ETM Data|\n|2010|CVAPS|Change Vector Analysis in Posterior Probability Space: A New Method for Land Cover Change Detection|[GRSL2010](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F5597922)|CVA, land cover change, postclassification comparison (PCC), posterior probability space| Multitemporal Landsat Thematic Mapper (TM) data for Shunyi District, Beijing, China|\n|2009|PCA-Kmeans|Unsupervised Change Detection in Satellite Images Using Principal Component Analysis and k-Means Clustering|[GRSL2009](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F5196726)|K-means clustering, multitemporal satellite images, optical images, principal component analysis (PCA)|The optical images of Lake Tahoe, Reno, Nevada|\n|2007|[IR-MAD](http:\u002F\u002Fpeople.compute.dtu.dk\u002Falan\u002Fsoftware.html) | The Regularized Iteratively Reweighted Multivariate Alteration Detection | [TIP2007](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F4060945) |Canonical correlation analysis (CCA), iteratively reweighted multivariate alteration detection (IR-MAD), MAD transformation, regularization or penalization|Partly Constructed Landsat TM Data, Northern Swede; SPOT HRV Data, Kiambu District, Kenya; Hymap Data, Lake Waging-Taching, Germany|\n|2003|ICVA|Land-Use\u002FLand-Cover Change Detection Using Improved Change-Vector Analysis|[PERS2003](https:\u002F\u002Fwww.ingentaconnect.com\u002Fcontent\u002Fasprs\u002Fpers\u002F2003\u002F00000069\u002F00000004\u002Fart00004)|Improved CVA, Double-Window Flexible Pace Search (DFPS), minimum-distance categorizing technique|Multitemporal Landsat TM Images of the Haidian District, Beijing, China|\n|1998|[MAD](http:\u002F\u002Fpeople.compute.dtu.dk\u002Falan\u002Fsoftware.html)|Multivariate Alteration Detection (MAD) and MAF Postprocessing in Multispectral, Bitemporal Image Data: New Approaches to Change Detection Studies|[RSE1998](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425797001624)|Multivariate Alteration Detection (MAD), Maximum Autocorrelation Factor (MAF), Canonical Correlation Analysis (CCA)|Two Landsat MSS images of Queensland, Australia; Two AVHRR images of El Niño stages in California Current System|\n|1980|CVA|Change Vector Analysis: An Approach for Detecting Forest Changes with Landsat|[LARS symposia 1980](https:\u002F\u002Fdocs.lib.purdue.edu\u002Fcgi\u002Fviewcontent.cgi?article=1386&context=lars_symp)|Change Vector Analysis, Forest Change Detection, Landsat Multispectral Data, Spatial-Spectral Clustering, Tasseled Cap Transformation| Landsat data covering three timber compartments in the Palouse District of Clearwater National Forest, Idaho|\n\n\n# Review Papers\n\n| Year | Title | Publication | Description |\n| :--- | :--- | :--- | :--- | \n|2025|遥感智能变化检测的深度学习方法：演变与发展趋势|[测绘学报2025](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002FjZp_79g-L_LTCJpNRDOMdQ)|本文系统综述了深度学习在遥感变化检测中的研究进展，围绕变化特征表达和网络学习策略两大核心问题，梳理了从局部到时空联合、单一到多模态、轻量到大模型、二值到多类别特征表达的发展趋势，以及从全监督向弱\u002F半监督和无监督学习的演进路径，并指出图文融合、生成式模型和人机协同是未来提升智能化水平的关键方向。|\n|2025|深度学习遥感变化检测研究进展：像素-对象-场景|[遥感技术与应用2025](http:\u002F\u002Fwww.rsta.ac.cn\u002FCN\u002F10.11873\u002Fj.issn.1004-0323.2025.4.0783)|本文从像素级、对象级和场景级三个层次系统总结深度学习在遥感变化检测中的研究进展，结合典型案例分析其实际应用，并展望其未来发展趋势。|\n| 2025 | On the use of Graphs for Satellite Image Time Series | [arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.16685) | Explores the integration of graph-based techniques for spatio-temporal analysis of satellite image time series, focusing on the construction of spatio-temporal graphs and their applications in tasks such as land cover mapping and water resource forecasting, along with future research perspectives. | \n| 2025 | A Survey of Sample-Efficient Deep Learning for Change Detection in Remote Sensing: Tasks, Strategies, and Challenges | [GRSM2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F10884556) | Summarizes literature on deep learning-based change detection methods for different tasks and strategies in sample-limited scenarios, discussing recent advances in image generation, self-supervision, and visual foundation models to address data scarcity. | \n| 2025 | Deep learning change detection techniques for optical remote sensing imagery: Status, perspectives and challenges | [JAG2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1569843224006381) | Systematically summarizes datasets, theories, and methods of change detection for optical remote sensing imagery, analyzing AI-based algorithms from the perspective of algorithm granularity and discussing challenges and trends in the AI era. Updates are available at [daifeng2016\u002FAwesome-Optical-Remote-Sensing-Datasets-and-Methods](https:\u002F\u002Fgithub.com\u002Fdaifeng2016\u002FAwesome-Optical-Remote-Sensing-Datasets-and-Methods). |\n| 2024 | Deep-Learning for Change Detection Using Multi-Modal Fusion of Remote Sensing Images: A Review | [RS2024](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F16\u002F20\u002F3852) | Explores the application of deep learning for change detection in remote sensing imagery using heterogeneous data sources, including multispectral, hyperspectral, radar, and multitemporal imagery, and discusses public datasets, models, challenges, and future trends. | \n| 2024 | Deep Learning for Satellite Image Time-Series Analysis: A review | [GRSM2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F10529247) | Summarizes state-of-the-art methods for modeling environmental and agricultural variables from satellite image time series (SITS) using deep learning, addressing the complexity of SITS data and its applications in land and natural resource management. | \n| 2024 | Advances and Challenges in Deep Learning-Based Change Detection for Remote Sensing Images: A Review through Various Learning Paradigms | [RS2024](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F16\u002F5\u002F804) | Comprehensively examines deep learning-based change detection in remote sensing, covering key architectures, learning paradigms (supervised, semi-supervised, weakly supervised, and unsupervised), benchmark datasets, and emerging opportunities such as self-supervised learning, foundation models, and multimodal data fusion, while highlighting current challenges and promising future research directions to advance the field. | \n| 2024 | Change Detection Methods for Remote Sensing in the Last Decade: A Comprehensive Review | [RS2024](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F16\u002F13\u002F2355) | Presents a comprehensive survey of deep learning-based change detection in remote sensing over the past decade, offering a systematic taxonomy from perspectives of algorithm granularity, supervision modes, and frameworks, while reviewing key datasets, evaluation metrics, state-of-the-art performance, and identifying promising future research directions to guide and inspire the community. | \n| 2023 | 深度学习的遥感变化检测综述：文献计量与分析 | [遥感学报2023](https:\u002F\u002Fwww.ygxb.ac.cn\u002Fzh\u002Farticle\u002Fdoi\u002F10.11834\u002Fjrs.20222156\u002F) | 本文综述了基于深度学习的遥感变化检测研究进展，从像素、对象和场景三个粒度系统梳理方法体系，指出对象与场景级方法更具优势，并强调未来需突破多模态异质数据融合、非理想样本处理及多元变化信息提取等挑战，以推动其在多领域更广泛、智能化的应用。 | \n| 2023 | 人工智能时代的遥感变化检测技术：继承、发展与挑战 | [遥感学报2023](https:\u002F\u002Fwww.ygxb.ac.cn\u002Fzh\u002Farticle\u002Fdoi\u002F10.11834\u002Fjrs.20222199\u002F) | 本文系统梳理了人工智能时代下光学遥感影像变化检测技术从传统方法向数据—模型—知识联合驱动的智能化转型历程，分析了无监督、监督与弱监督三类方法的发展趋势，并指出未来需重点突破模型可解释性、泛化迁移能力及跨场景跨领域应用等关键瓶颈问题。相关讲解视频详见：[【前沿进展】变化检测与深度学习](https:\u002F\u002Fwww.bilibili.com\u002Fvideo\u002FBV1Cf4y1Y77x\u002F?vd_source=22b45bd19426f7fd4ee5b0e1055bfc8c)。 | \n| 2023 | 3D urban object change detection from aerial and terrestrial point clouds: A review | [JAG2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1569843223000808) | Reviews developments in 3D change detection for urban objects using point cloud data, analyzing buildings, street scenes, urban trees, and construction sites, and discusses data sources, methods, and future challenges. | \n| 2023 | Change detection of urban objects using 3D point clouds: A review | [ISPRS P&RS 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271623000163) | Provides a comprehensive review of point-cloud-based 3D change detection for urban objects, covering data registration, variance estimation, change analysis, and applications in land cover monitoring, vegetation surveys, and construction automation. | \n|2022|Land Cover Change Detection With Heterogeneous Remote Sensing Images: Review, Progress, and Perspective|[IEEE PROC 2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9955391)|Provides a comprehensive overview of heterogeneous remote sensing image change detection (Hete-CD), summarizing its literature, major techniques, datasets, performance evaluations, challenges, and future directions to serve as a one-stop reference for researchers and practitioners.|\n|2022|Deep learning for change detection in remote sensing: a review|[GSIS2022](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F10095020.2022.2085633)|Analyzes why deep learning enhances remote sensing change detection by examining its improved information representation, methodological advances, and performance gains across spectral, spatial, temporal, and multi-sensor dimensions, while also identifying key limitations and future directions for deep learning change detection development.|\n| 2022 | Land Cover Change Detection Techniques: Very-high-resolution optical images: A review | [GRSM2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9477629) | Reviews land cover change detection techniques using very-high-resolution remote sensing images, focusing on the ability to capture detailed changes and discussing various methods and applications. | \n| 2022 | A Survey on Deep Learning-Based Change Detection from High-Resolution Remote Sensing Images | [RS2022](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F14\u002F7\u002F1552) | Reviews deep learning-based change detection methods for high-resolution remote sensing images, categorizing algorithms by network architecture, and discusses datasets, evaluation metrics, challenges, and future research directions. | \n|2022|A review of multi-class change detection for satellite remote sensing imagery|[GSIS2022](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F10095020.2022.2128902)|Provides a comprehensive review of Multi-class Change Detection (MCD) in remote sensing, covering its background, key challenges, benchmark datasets, methodological categories, real-world applications, and future research directions, aiming to fill the gap in existing literature and serve as a foundational reference for advancing fine-grained land change analysis beyond traditional binary detection.|\n|2021|Change Detection From Very-High-Spatial-Resolution Optical Remote Sensing Images: Methods, applications, and future directions|[GRSM2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9395350)|Provides a comprehensive overview of change detection in very-high-spatial-resolution (≤5 m) remote sensing images, systematically examining current methods, real-world applications, and future research directions to address challenges such as limited spectral information, spectral variability, and geometric distortions.|\n| 2020 | A survey of change detection methods based on remote sensing images for multi-source and multi-objective scenarios | [RS2020](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F12\u002F15\u002F2460) | Surveys change detection methods for multi-source remote sensing images and multi-objective scenarios, summarizing a general framework including change information extraction, data fusion, and analysis, and discusses future directions. | \n| 2020 | Change Detection Based on Artificial Intelligence: State-of-the-Art and Challenges | [RS2020](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F12\u002F10\u002F1688) | Reviews the state-of-the-art methods, applications, and challenges of AI for change detection, covering data sources, deep learning frameworks, and unsupervised schemes, and discusses issues like heterogeneous data processing and AI reliability. Updates are available at [MinZHANG-WHU\u002FChange-Detection-Review](https:\u002F\u002Fgithub.com\u002FMinZHANG-WHU\u002FChange-Detection-Review).| \n| 2019 | A Review of Change Detection in Multitemporal Hyperspectral Images: Current Techniques, Applications, and Challenges | [GRSM2019](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8738052) | Presents a comprehensive review of change detection in hyperspectral remote sensing images, covering fundamental concepts, methodological categories, current techniques, and key challenges, while demonstrating state-of-the-art approaches through experimental results to highlight the unique potential and complexity of exploiting high spectral resolution for fine-scale land-cover change monitoring. | \n|2018|多时相遥感影像变化检测方法综述|[武汉大学学报 (信息科学版) 2018](http:\u002F\u002Fch.whu.edu.cn\u002Farticle\u002Fid\u002F6272)|本文系统回顾了多时相遥感影像变化检测技术的发展历程，从预处理、方法分类到精度评价全面梳理研究进展，指出当前尚无普适性通用方法，并分析核心难点与应对策略，旨在推动该领域向更深入、更系统方向发展。|\n|2017|多时相遥感影像变化检测的现状与展望|[测绘学报2017](https:\u002F\u002Fhtml.rhhz.net\u002FCHXB\u002Fhtml\u002F2017-10-1447.htm)|本文围绕多时相遥感影像变化检测的基本流程，从预处理、方法、阈值分割到精度评价系统梳理最新研究进展，总结其在生态环境监测与城市发展等领域的应用，并展望高光谱与高分辨率影像驱动下的未来发展方向。|\n| 2017 | Change detection using landsat time series: A review of frequencies, preprocessing, algorithms, and applications | [ISPRS P&RS 2017](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS092427161730103X) | Reviews change detection studies based on Landsat time series, covering frequencies, preprocessing steps, algorithms, and applications, and discusses the impact of free access to Landsat data on change detection methodologies. | \n| 2016 | Optical remotely sensed time series data for land cover classification: A review | [ISPRS P&RS 2016](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271616000769) | Reviews the use of optical remote sensing time series data for land cover classification, discussing issues and opportunities in generating annual land cover products and methods for incorporating time series information. | \n|2016|SAR影像变化检测研究进展|[计算机研究与发展2015](https:\u002F\u002Fcrad.ict.ac.cn\u002Fcn\u002Farticle\u002FY2016\u002FI1\u002F123)|本文系统梳理了SAR影像变化检测的经典流程与传统方法，重点综述近年来在差异图生成及阈值、聚类、图切、水平集等分析方法上的新兴算法改进，并通过两组数据集定量验证其性能，最后展望了该领域仍需深入研究的关键方向。|\n| 2015 | A critical synthesis of remotely sensed optical image change detection techniques | [RSE2015](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425715000152) | Provides a critical synthesis of remote sensing change detection techniques, organizing the literature by unit of analysis and comparison method to reduce conceptual overlap and guide future research. | \n| 2013 | Change detection from remotely sensed images: From pixel-based to object-based approaches | [ISPRS P&RS 2013](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271613000804) | Reviews change detection methodologies from pixel-based to object-based approaches, discussing the potential of object-based methods and data mining techniques with the advent of very-high-resolution imagery. | \n| 2012 | Object-based change detection | [IJRS2012](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Fabs\u002F10.1080\u002F01431161.2011.648285) | Discusses object-based change detection (OBCD) using high-spatial-resolution imagery, comparing it with pixel-based approaches and reviewing algorithms and applications for detailed change information extraction. | \n| 2012 | A review of large area monitoring of land cover change using Landsat data | [RSE2012](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425712000314) | Reviews methods for large area monitoring of land cover change using Landsat data, focusing on forest cover change, and discusses radiometric correction, temporal updating, and the impact of free access to terrain-corrected data. | \n|2011|多时相遥感影像变化检测综述|[地理信息世界2011](https:\u002F\u002Fd.wanfangdata.com.cn\u002Fperiodical\u002FCh9QZXJpb2RpY2FsQ0hJTmV3UzIwMjUwMTE2MTYzNjE0Eg9kbHh4c2oyMDExMDIwMDcaCDZ4ejNuZmt5)|本文系统回顾多时相遥感影像变化检测的发展现状，从环境变化特性出发，围绕预处理、方法分类、精度评估等四大方面梳理技术演进，并提出融合多源数据、集成处理与智能方法的综合解决方案，同时指出当前挑战与应对策略，以推动该领域深入发展。|\n| 2005 | Image change detection algorithms: a systematic survey | [TIP2004](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F1395984) | Provides a systematic survey of image change detection algorithms, covering common processing steps and core decision rules, and discusses preprocessing methods, consistency enforcement, and performance evaluation principles. | \n| 2004 | Digital change detection methods in ecosystem monitoring: a review | [IJRS2004](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Fabs\u002F10.1080\u002F0143116031000101675) | Reviews digital change detection methods in ecosystem monitoring, covering multi-temporal, multi-spectral data techniques, preprocessing routines, and change detection algorithms, and highlights the complementarity between different methods. | \n| 2004 | Change detection techniques | [IJRS2004](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Fabs\u002F10.1080\u002F0143116031000139863) | Summarizes and reviews change detection techniques using remote sensing data, highlighting image differencing, principal component analysis, and post-classification comparison as common methods, and discusses emerging techniques like spectral mixture analysis and neural networks. | \n|2003|利用遥感影像进行变化检测|[武汉大学学报 (信息科学版) 2003](http:\u002F\u002Fch.whu.edu.cn\u002Fcn\u002Farticle\u002Fpdf\u002Fpreview\u002F4718.pdf)|本文针对遥感影像变化检测的紧迫需求与技术难点，提出影像配准与变化检测同步求解的新思路，并探讨其拓展至三维变化检测的可行性，系统比较七类主流方法，最后指明未来重点研究方向。|\n\n\n# Competitions\n\n| Year | Target | Contest | Track | Image Pairs | Image Size | Resolution |Other|\n| --- | --- | --- | --- | --- | --- | --- | --- |\n|2025|Building|[AI for Earthquake Response](https:\u002F\u002Fplatform.ai4eo.eu\u002Fai-for-earthquake-response)|Detect damaged vs. undamaged buildings by analyzing high-resolution pre- and post-event satellite imagery|-|-|-|-|\n| 2024 | Land cover| [ISPRS第一技术委员会多模态遥感应用算法智能解译大赛](https:\u002F\u002Fwww.gaofen-challenge.com\u002Fchallenge) |基于高分辨率可见光图像的感兴趣区域内部变化智能检测| 4,000 | 512×512 | 2m |-|\n| 2024 | Land cover | [“吉林一号”杯卫星遥感应用青年创新创业大赛](https:\u002F\u002Fwww.jl1mall.com\u002Fcontest\u002FmatchMenu) |高分辨率遥感影像全要素变化检测研究| 5,000 | 512×512 |\u003C0.75m|-|\n| 2023 | Cropland | [“吉林一号”杯卫星遥感应用青年创新创业大赛](https:\u002F\u002Fwww.jl1mall.com\u002Fcontest\u002Fmatch\u002Finfo?id=1645664411716952066) |基于高分辨率卫星影像的耕地变化检测| 8,000 | 256×256 |\u003C0.75m|-|\n| 2023 | Land cover | [“国丰东方慧眼杯”遥感影像智能处理算法大赛](http:\u002F\u002Frsipac.whu.edu.cn\u002F) |对象级变化检测| >6,000 | 512×512 | 1-2m |-|\n| 2022 | Land cover | [“航天宏图杯”遥感影像智能处理算法大赛](http:\u002F\u002Frsipac.whu.edu.cn\u002F) |遥感影像变化检测| >6,000 | 512×512 | 1-2m |-|\n| 2022 | Flood | [SpaceNet8: Flood Detection Challenge](https:\u002F\u002Fjoin.topcoder.com\u002Fspacenet) | Flood Detection Challenge Using Multiclass Segmentation | 12 | 1,300×1,300 | 0.3-0.8m |[Dataset Paper](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2022W\u002FEarthVision\u002Fpapers\u002FHansch_SpaceNet_8_-_The_Detection_of_Flooded_Roads_and_Buildings_CVPRW_2022_paper.pdf), [Solution Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10281500)|\n| 2021 |Land cover|[IEEE GRSS Data Fusion Contest](https:\u002F\u002Fwww.grss-ieee.org\u002Fcommunity\u002Ftechnical-committees\u002F2021-ieee-grss-data-fusion-contest-track-msd\u002F)|Multitemporal Semantic Change Detection|2,250|-|-|[Outcome Paper](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9690575)|\n| 2021 |Land cover|[DynamicEarthNet Challenge](https:\u002F\u002Fcodalab.lisn.upsaclay.fr\u002Fcompetitions\u002F2882) | Weakly-Supervised Unsupervised Binary Land Cover Change Detection, Multi-Class Change Detection|54,750|1,024x1,024|3.0|[Top1 Solution](https:\u002F\u002Fgithub.com\u002Fsolcummings\u002Fearthvision2021-weakly-supervised), [Dataset Paper](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2022\u002Fpapers\u002FToker_DynamicEarthNet_Daily_Multi-Spectral_Satellite_Dataset_for_Semantic_Change_Segmentation_CVPR_2022_paper.pdf)|\n| 2021 | Land cover | [“昇腾杯”遥感影像智能处理算法大赛](http:\u002F\u002Frsipac.whu.edu.cn\u002Fsubject_two_2021) | 耕地建筑物变化检测 | >6,000 | 512×512 | 1-2m |[Top4 Solution](https:\u002F\u002Fgithub.com\u002FWangZhenqing-RS\u002F2021rsipac_changeDetection_TOP4), [Top5 Solution](https:\u002F\u002Fgithub.com\u002F78666621\u002F2021rsipac_changeDetection_TOP5)|\n| 2021 | Building | [遥感图像智能解译技术挑战赛](https:\u002F\u002Fcaptain-whu.github.io\u002FPRCV2021_RS\u002Ftasks.html) | 遥感图像建筑物变化检测 | 10,000 | 512×512 | - |-|[Top2 Solution](https:\u002F\u002Fgithub.com\u002Fbusiniaoo\u002FPRCV2021-Change-Detection-Contest-2nd-place-Solution), [Top3 Solution](https:\u002F\u002Fgithub.com\u002Flikyoo\u002FPRCV2021_ChangeDetection_Top3)|\n| 2021 | Building | [慧眼“天智杯”人工智能挑战赛](https:\u002F\u002Frsaicp.com\u002Fportal\u002FcontestList) |可见光建筑智能变化检测| 5,000 | 1,024×1,024 | 0.5-0.7m |-|\n| 2020 | Land cover | [商汤科技首届AI遥感解译大赛](https:\u002F\u002Fsenseearth-cloud.com\u002F) |变化检测|4,662 | 512×512 | 0.5-3m |[Top1 Solution](https:\u002F\u002Fgithub.com\u002FLiheYoung\u002FSenseEarth2020-ChangeDetection)|\n| 2020 | Land cover | [SpaceNet 7: Multi-Temporal Urban Development Challenge](https:\u002F\u002Fmedium.com\u002Fthe-downlinq\u002Fthe-spacenet-7-multi-temporal-urban-development-challenge-dataset-release-9e6e5f65c8d5) | Multi-Temporal Urban Development Challenge |-|1,024×1,024| 4m |[Solutions](https:\u002F\u002Fgithub.com\u002FSpaceNetChallenge\u002FSpaceNet7_Multi-Temporal_Solutions), [Dataset Paper](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2021\u002Fpapers\u002FVan_Etten_The_Multi-Temporal_Urban_Development_SpaceNet_Dataset_CVPR_2021_paper.pdf)|\n| 2019 | Building | [xView2 Challenge](https:\u002F\u002Fxview2.org\u002Fdataset) (or xBD) | Building Damage Assessment | 11,034 | 1,024×1,024 | - |[Dataset Paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.09296)|\n\n\n# Satellite Data Resources for Disaster Response\n\n| Name | Description |\n| --- | --- | \n|[Maxar Open Data Program](https:\u002F\u002Fwww.maxar.com\u002Fopen-data)  |The Maxar Open Data Program provides pre- and post-event satellite imagery (from WorldView-3 and other sensors) for select sudden-onset major crises, along with crowdsourced damage assessments.|\n|[吉林一号资源库](https:\u002F\u002Fwww.jl1mall.com\u002Fresrepo\u002F?fromUrl=https:\u002F\u002Fwww.jl1mall.com\u002Fedu)|提供高分辨率卫星影像和专题数据，支持自然灾害监测、农业估产、生态环境保护、水利管理及应急响应等多领域应用。部分数据集仅限教育认证用户。|\n|[Planet Disaster Datasets](https:\u002F\u002Fwww.planet.com\u002Fdisasterdata\u002F) |Planet makes available select imagery for major disaster events, including major earthquakes, floods, storms, wildfires, and human-made disasters. To download the data, users must complete a form for access qualification.|\n|[The International Charter: Space And Major Disasters](https:\u002F\u002Fdisasterscharter.org\u002F)|Disaster mapping results and analyses are available for various global hazards, but the underlying satellite imagery is not directly provided.|\n\n\n# More Resources\n\n| Name | Description |\n| --- | --- | \n|[Hansen Global Forest Change](https:\u002F\u002Fglad.earthengine.app\u002Fview\u002Fglobal-forest-change) ([GEE dataset](https:\u002F\u002Fdevelopers.google.com\u002Fearth-engine\u002Fdatasets\u002Fcatalog\u002FUMD_hansen_global_forest_change_2023_v1_11))|Annual global tree cover loss and gain maps at 30m resolution (2000–present), widely used as ground-truth labels and evaluation data for forest change detection research. Produced by the GLAD lab at the University of Maryland. Full-resolution GeoTIFFs are also available via [earthenginepartners.appspot.com](https:\u002F\u002Fearthenginepartners.appspot.com\u002Fscience-2013-global-forest\u002Fdownload_v1.11.html).|\n|[daifeng2016\u002FAwesome-Optical-Remote-Sensing-Datasets-and-Methods](https:\u002F\u002Fgithub.com\u002Fdaifeng2016\u002FAwesome-Optical-Remote-Sensing-Datasets-and-Methods?tab=readme-ov-file)|This repository is for summarizing the latest optical remote sensing datasets and methods, which are listed in review article: *Deep learning change detection techniques for optical remote sensing imagery: Status, perspectives and challenges*, published in [JAG2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1569843224006381).|\n|[MinZHANG-WHU\u002FChange-Detection-Review](https:\u002F\u002Fgithub.com\u002FMinZHANG-WHU\u002FChange-Detection-Review)|A review of change detection methods, including codes and open datasets for deep learning. From paper: *Change Detection Based on Artificial Intelligence: State-of-the-Art and Challenges*, published in [RS2020](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F12\u002F10\u002F1688). |\n|[DoongLi\u002FAwesome-Scene-Change-Detection](https:\u002F\u002Fgithub.com\u002FDoongLi\u002FAwesome-Scene-Change-Detection)|This repository curates a comprehensive list of resources for scene change detection, including papers, videos, code, and relevant websites. While many change detection studies focus on remote sensing, this collection is specifically dedicated to works tested on street-view scenes and primarily covers methods based on robot vision (especially using image and point cloud data)|\n\n\n# Citation\n\nIf you find our project useful in your research, please consider citing:\n\n```latex\n@misc{awesome_rscd_2019,\n    title={Awesome Remote Sensing Change Detection},\n    author={Awesome RSCD Contributors},\n    howpublished = {\\url{https:\u002F\u002Fgithub.com\u002Fwenhwu\u002Fawesome-remote-sensing-change-detection}},\n    year={2019}\n}\n```\n","# \u003Cp align=center>`超赞的遥感变化检测`\u003C\u002Fp>\n[![Awesome](https:\u002F\u002Fcdn.rawgit.com\u002Fsindresorhus\u002Fawesome\u002Fd7305f38d29fed78fa85652e3a63e154dd8e8829\u002Fmedia\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fsindresorhus\u002Fawesome) [![维护中](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FMaintained%3F-yes-green.svg)](https:\u002F\u002FGitHub.com\u002FNaereen\u002FStrapDown.js\u002Fgraphs\u002Fcommit-activity) [![欢迎提交PR](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-welcome-brightgreen.svg?style=flat)](http:\u002F\u002Fmakeapullrequest.com) [![使用Markdown制作](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FMade%20with-Markdown-1f425f.svg)](http:\u002F\u002Fcommonmark.org)![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fwenhwu\u002Fawesome-remote-sensing-change-detection?style=social)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwenhwu\u002Fawesome-remote-sensing-change-detection?style=social)![最近一次提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fwenhwu\u002Fawesome-remote-sensing-change-detection.svg?style=flat&logo=github&label=Last%20Commit)[![许可证：MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-blue.svg)](https:\u002F\u002Fopensource.org\u002Flicenses\u002FMIT)\n\n这是一份全面且最新的遥感变化检测相关资源合集，涵盖了数据集、工具、方法（包括基础模型、扩散模型、Transformer和CNN等）、综述论文以及竞赛信息。\n\n# 目录\n\n- [数据集](#datasets)\n  - [光学数据集](#optical-datasets)\n  - [多模态与SAR数据集](#multi-modal-and-sar-datasets)\n- [工具](#tools)\n- [方法](#methods)\n  - [深度学习](#deep-learning)\n    - [基础模型](#foundation-models)\n    - [扩散模型与GAN](#diffusion-models-and-gans)\n    - [Transformer](#transformers)\n    - [CNN](#cnns)\n  - [传统方法](#traditional-methods)\n    - [常用方法](#common-methods)\n    - [新方法](#new-methods)\n- [综述论文](#review-papers)\n- [竞赛](#competitions)\n- [灾害响应卫星数据资源](#satellite-data-resources-for-disaster-response)\n- [更多资源](#more-resources)\n- [引用](#citation)\n\n\n# 数据集\n\n* SCD：语义变化检测，BCD：二值变化检测，DDA：灾害损毁评估，BDA：建筑物损毁评估，RSICC：遥感图像变化描述\n\n## 光学数据集\n\n|年份|任务|目标|数据集 |出版物|来源|图像对数 |图像尺寸|分辨率|地点|类别|\n|:---|:--- |:--- | :------| :------|:----------| :-------| :-------| :----------- | :----- | :---- |\n|2025|SCD+BCD|建筑物|[RSCC](https:\u002F\u002Fgithub.com\u002FBili-Sakura\u002FRSCC)|[NeurIPS2025](https:\u002F\u002Fopenreview.net\u002Fforum?id=yn2fJYBKEB)|Open Maxar Data Programme |62,351|512 × 512|0.3-0.8m|全球31个地点|5|\n|2026|SCD|土地覆盖|[LsSCD-Ex](https:\u002F\u002Fgithub.com\u002Ftangkai-RS\u002FDreamCD)|[JAG2026](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.jag.2026.105125)|Google Earth|100|2048 × 2048|0.6m|中国南京|8|\n|2026|SCD+BCD|建筑物|[FOTBCD-Binary;FOTBCD-Instances](https:\u002F\u002Fgithub.com\u002Fabdelpy\u002FFOTBCD-datasets)|[arXiv2026](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.22596)|IGN|27,871;4000|512 × 512|0.2m|法国|2;3|\n|2025|RSICC|土地覆盖|[MOSAIC-SEN2-CC](https:\u002F\u002Fgithub.com\u002FChangeCapsInRS\u002FMOSAIC-SEN2-CC)|[JSTARS2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11181102\u002F)|Sentinel-2|5,232|480 × 480|10m|全球|8|\n|2025|SCD|耕地|[厦门](https:\u002F\u002Fgithub.com\u002Flong123524\u002FCPGNet), [福州](https:\u002F\u002Fgithub.com\u002Flong123524\u002FHGINet-torch)|[JAG2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1569843225005631?dgcid=rss_sd_all), [ISPRS P&RS 2024](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271624001709)|Google Earth|6480 (厦门); 8719 (福州)|256 × 256|0.5m|中国厦门翔安区和同安区；福州长乐区和闽侯区|7|\n|2025|SCD+BCD|土地覆盖|[WHU-GCD](https:\u002F\u002Fgpcv.whu.edu.cn\u002Fdata\u002FWHU_Generative_Change_Detection_Dataset.html)|[ISPRS P&RS 2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271625001595?dgcid=rss_sd_all)|LoveDA、Evlab-SS、LandCover.ai和Google Earth；DSIFN-CD、LEVIR-CD、SECOND、CLCD、CNAM-CD|28,067|512 × 512|-|全球|26|\n|2025|BCD|建筑物|[CWSCD](https:\u002F\u002Fgithub.com\u002Fyuruqingsi\u002FCWSCD-dataset)|[JAG2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1569843225005084?dgcid=rss_sd_all)|BJ-2、GF-2|200|2048×2048|1m|中国河北|2|\n|2025|BCD|建筑物|DVCD|[arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.17944)|无人机影像|12,833|-|0.1m|中国广东|2|\n|2025|SCD|土地覆盖|[SC-SCD7, CC-SCD5](https:\u002F\u002Fgithub.com\u002FStephenApX\u002FMTL-TripleS)|[ISPRS P&RS 2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271625003776?dgcid=rss_sd_all)|Pléiades、北京-2、高分-1、高分-2、资源三号|1,722; 953|512×512|0.5m、2.3m、2.5 m|中国漳州（龙文）和河南（登封、洛阳、三门峡）|8; 5|\n|2025|SCD|土地覆盖|[LevirSCD](https:\u002F\u002Fgithub.com\u002Fzmoka-zht\u002FFoBa)|[arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.15788)|GF-1、Google Earth|3,225|256×256|1-2|中国北京|16|\n|2025|BCD|土地覆盖|[JL1-CD](https:\u002F\u002Fgithub.com\u002FcircleLZY\u002FMTKD-CD)|[arXiv2025](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2502.13407)|吉林-1|5,000|512×512|0.5-0.75m|中国多个省份|2|\n|2025|SCD|建筑物|[EBD](https:\u002F\u002Ffigshare.com\u002Farticles\u002Ffigure\u002FAn_Extended_Building_Damage_EBD_dataset_constructed_from_disaster-related_bi-temporal_remote_sensing_images_\u002F25285009\u002F2)|[JRS2025](https:\u002F\u002Fspj.science.org\u002Fdoi\u002Ffull\u002F10.34133\u002Fremotesensing.0733?af=R)|WorldView-3|>18,000|512×512|0.3-0.5m|全球|7|\n|2025|SCD|土地利用|[MLCD](https:\u002F\u002Faistudio.baidu.com\u002Fdataset\u002Fdetail\u002F245516\u002Fintro)|[JSTARS2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11058393)|Google Earth Engine|10,000|256×256|0.5-2m|中国澳门|\n|2024|BCD|矿山| [MineNetCD](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002FHZDR-FWGEL\u002FMineNetCD256) |[TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10744421) |Google Earth|71,711|256×256| 1.2m |全球|2|\n|2024|BCD|建筑物| [TUE-CD](https:\u002F\u002Fgithub.com\u002FRSMagneto\u002FMSI-Net)| [TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10623278)|WorldView-2|1,656|256×256|1.8m|土耳其|2|\n|2024|SCD|城市|[MSRS-CD](https:\u002F\u002Fgithub.com\u002Fbobo59\u002FMSRSCD)|[JSTARS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10813409)|-|841|1,024×1,024|0.5m|中国南方城市|5|\n|2024|SCD|耕地| [CropSCD](https:\u002F\u002Fgithub.com\u002Flsmlyn\u002FCropSCD)| [TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10579791) |-|4,141|512×512|0.5-2m|中国广东|9|\n|2024|SCD|耕地| [Hi-CNA](https:\u002F\u002Frsidea.whu.edu.cn\u002FHi-CNA_dataset.htm) |[ISPRS P&RS 2024](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271624002090) |GF-2|6,797| 512×512|0.8m|中国（河北、山西、山东和湖北）|5|\n|2024|SCD|土地覆盖|[ChangNet](https:\u002F\u002Fgithub.com\u002Fjankyee\u002FChangeNet)| [ICASSP2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10446592)|WayBack|31,000|1,900×1,200|0.3m|中国100个城市|6|\n|2023|SCD|耕地|[JL1](https:\u002F\u002Fwww.jl1mall.com\u002Fresrepo\u002F?fromUrl=https:\u002F\u002Fwww.jl1mall.com\u002Fedu)|-|吉林-1|8,000 | 256×256 |\u003C0.75m|-|9|\n|2023|BCD|建筑物| [EGY-BCD](https:\u002F\u002Fgithub.com\u002Foshholail\u002FEGY-BCD)| [GRSL2023](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10145434)|Google Earth |6,091 | 256×256| 0.25m|埃及|2|\n|2023|BCD|建筑物| [HRCUS-CD](https:\u002F\u002Fgithub.com\u002Fzjd1836\u002FAERNet)| [TGRS2023](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10209204)|-|11,388 |256×256| 0.5m|中国珠海|2|\n|2023|BCD|建筑物| [SI-BU](https:\u002F\u002Fvrlab.org.cn\u002F~hanhu\u002Fprojects\u002Fbcenet\u002F)| [ISPRS P&RS 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271623001284?via%3Dihub)|Google Earth|4,932|512×512| 0.2m|中国贵阳|2|\n|2023|SCD|土地覆盖|[CNAM-CD](https:\u002F\u002Fgithub.com\u002FSilvestezhou\u002FCNAM-CD)| [RS2023](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F15\u002F9\u002F2464)|Google Earth|2,503|512×512|0.5m|中国12个国家级新区|6|\n|2023|SCD|土地覆盖| [WUSU](https:\u002F\u002Frsidea.whu.edu.cn\u002Fresource_wusu_sharing.htm)| [IJDE2023](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F17538947.2023.2246445)|GF-2|3| 6,358×6,382 \u002F 7,025×5,500| 1m |中国武汉|12|\n|2023|BCD|滑坡| [GVLM](https:\u002F\u002Fgithub.com\u002Fzxk688\u002FGVLM)| [ISPRS P&RS 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271623000242)|Google Earth|17| 1,748×1,748-10,808×7,424|0.59m|全球|2|\n|2023|SCD|建筑物|[BANDON](https:\u002F\u002Fgithub.com\u002Ffitzpchao\u002FBANDON)| [Sci. China Inf. Sci. 2023](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs11432-022-3691-4)|Google Earth、Microsoft Virtual Earth和ArcGIS|2,283|2,048×2,048| 0.6m|中国（北京、上海、武汉、深圳、香港和济南）|6|\n|2023|SCD|土地覆盖| [DynamicEarthNet](https:\u002F\u002Fmediatum.ub.tum.de\u002F1650201) | [CVPR2022](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2022\u002Fhtml\u002FToker_DynamicEarthNet_Daily_Multi-Spectral_Satellite_Dataset_for_Semantic_Change_Segmentation_CVPR_2022_paper.html) |PlanetFusion|54,750|1,024×1,024|3m|全球|7|\n|2022|BCD|道路|[CRCD、WRCD](http:\u002F\u002Fwww.lmars.whu.edu.cn\u002Fsuihaigang\u002Findex)|[TITS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9815123)|航空影像、Google Earth|3,237, 1,960|512×512|0.2m、1.14m|新西兰基督城；中国武汉江夏区|2|\n|2022|BCD|耕地| [CLCD](https:\u002F\u002Fgithub.com\u002Fliumency\u002FCropLand-CD)| [JSTARS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9780164)|GF-2|600|512×512|0.5-2m|中国广东|2|\n|2022|RSICC|建筑物 | [LEVIR-CC](https:\u002F\u002Fgithub.com\u002FChen-Yang-Liu\u002FRSICC)  | [TGRS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9934924)|Google Earth|10,077| 1,024×1,024| 0.5m|美国德克萨斯州|2|\n|2022|BCD|土地覆盖 | [SYSU-CD](https:\u002F\u002Fgithub.com\u002Fliumency\u002FSYSU-CD)    | [TGRS2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9467555) |-|20,000| 256×256 | 0.5m |中国香港 |2|\n|2022|SCD|建筑物| [S2Looking](https:\u002F\u002Fgithub.com\u002FS2Looking\u002FDataset)|[RS2021](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F13\u002F24\u002F5094) |GF、SuperView、BJ-2|5,000| 1,024×1,024| 0.5-0.8m|全球|2|\n|2022|BCD|建筑物| [LEVIR-CD+](https:\u002F\u002Fgithub.com\u002FS2Looking\u002FDataset)|[RS2021](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F13\u002F24\u002F5094) |Google Earth|985|1,024×1,024|0.5m|美国德克萨斯州|2|\n|2022|SCD|土地覆盖| [Landsat-SCD](https:\u002F\u002Ffigshare.com\u002Farticles\u002Ffigure\u002FLandsat-SCD_dataset_zip\u002F19946135\u002F1)|[IJDE2022](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F17538947.2022.2111470) |Landsat|8,468|416×416|30m|中国新疆|10|\n|2022|SCD|建筑物|[NanjingDataset](https:\u002F\u002Fgithub.com\u002FSianGIS\u002FNanjingDataset)|[ISPRS P&RS 2022](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271622001344)|Google Earth|2,519|256×256|0.3m|中国南京|3|\n|2022|RSICC|城市|[Dubai-CC](https:\u002F\u002Fdisi.unitn.it\u002F~melgani\u002Fdatasets.html)|[TGRS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9847254)|Landsat 7|500|50×50|30m|迪拜|6|\n|2022|SCD|洪水|[SpaceNet 8](https:\u002F\u002Fjoin.topcoder.com\u002Fspacenet) | [CVPR2022W](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2022W\u002FEarthVision\u002Fpapers\u002FHansch_SpaceNet_8_-_The_Detection_of_Flooded_Roads_and_Buildings_CVPRW_2022_paper.pdf)|Maxar| 12 | 1,300×1,300 | 0.3-0.8m |德国和路易斯安那州|4|\n|2021|SCD|土地覆盖|[MSD](https:\u002F\u002Fwww.grss-ieee.org\u002Fcommunity\u002Ftechnical-committees\u002F2021-ieee-grss-data-fusion-contest-track-msd\u002F)|[JSTARS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9690575)|NAIP、Landsat-8和NLCD|2,250|-|1m、30m|美国马里兰|16|\n|2021|SCD|土地覆盖| [S2MTCP](https:\u002F\u002Fzenodo.org\u002Frecords\u002F4280482)|[ICPR2021](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-68787-8_42)|Sentinel-2|1,520|600×600|10m|全球|-|\n|2021|BCD|城市|[HTCD](https:\u002F\u002Fgithub.com\u002FShaoRuizhe\u002FSUNet-change_detection) |[RS2021](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F13\u002F18\u002F3750\u002Fhtm)|Google Earth、Open Aerial Map|3,772|256×256、2,048×2,048|0.5971m、0.07465m|摩尔多瓦基希讷乌|2|\n|2020|BCD|建筑物| [GZ-CD](https:\u002F\u002Fgithub.com\u002Fdaifeng2016\u002FChange-Detection-Dataset-for-High-Resolution-Satellite-Imagery) (或 CD_Data_GZ)|[TGRS2020](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9161009)|Google Earth|19| 1,006×1,168-4,936×5,224| 0.55m|中国广州|2|\n|2020|BCD|建筑物| [DSIFN](https:\u002F\u002Fgithub.com\u002FGeoZcx\u002FA-deeply-supervised-image-fusion-network-for-change-detection-in-remote-sensing-images\u002Ftree\u002Fmaster\u002Fdataset) (或 DSIFN-CD)|[ISPRS P&RS 2020](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271620301532?via%3Dihub) |Google Earth|3,940 | 512×512|-|中国（北京、成都、深圳、重庆、武汉和西安）|2|\n|2020|BCD|建筑物| [LEVIR-CD](https:\u002F\u002Fjustchenhao.github.io\u002FLEVIR\u002F)| [RS2020](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F12\u002F10\u002F1662)|Google Earth|637| 1,024×1,024|0.5m|美国德克萨斯州|2|\n|2020|SCD|土地覆盖| [Hi-UCD](https:\u002F\u002Fgithub.com\u002FDaisy-7\u002FHi-UCD-S?tab=readme-ov-file)|[arXiv2020](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.03247) |航空影像|1,293|1,024×1,024|0.1m|爱沙尼亚塔林|9|\n|2020|SCD|土地覆盖| [SECOND](https:\u002F\u002Fcaptain-whu.github.io\u002FSCD\u002F)| [TGRS2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9555824)|航空影像 |4,662|512×512| -  |中国（杭州、成都和上海）|6|\n|2020|BCD| 建筑物 | [MUDS](https:\u002F\u002Fmedium.com\u002Fthe-downlinq\u002Fthe-spacenet-7-multi-temporal-urban-development-challenge-dataset-release-9e6e5f65c8d5) (或 SpaceNet 7) | [CVPR2021](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2021\u002Fpapers\u002FVan_Etten_The_Multi-Temporal_Urban_Development_SpaceNet_Dataset_CVPR_2021_paper.pdf)|-|-|1,024×1,024|4m|全球|2|\n|2019|BDA|建筑物| [xBD](https:\u002F\u002Fxview2.org\u002Fdataset) | [arXiv2019](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.09296) |Maxar| 11,034 | 1,024×1,024 | \u003C0.8m |全球|4|\n|2019|SCD|土地覆盖| [HRSCD](https:\u002F\u002Fieee-dataport.org\u002Fopen-access\u002Fhrscd-high-resolution-semantic-change-detection-dataset)| [CVIU2019](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1077314219300992)|IGN|291|10,000×10,000|0.5m|法国（雷恩和卡昂）|5|\n|2018|BCD|建筑物| [WHU-CD](https:\u002F\u002Fstudy.rsgis.whu.edu.cn\u002Fpages\u002Fdownload\u002Fbuilding_dataset.html)| [TGRS2018](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8444434)|航空影像|1|32,507×15,354|0.2m|新西兰基督城|2|\n|2018|BCD|建筑物| [CDD](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1GX656JqqOyBi_Ef0w65kDGVto-nHrNs9\u002Fedit?pli=1) (或 SVCD)| [Int. Arch. Photogramm. Remote Sens. Spatial Inf. 2018](https:\u002F\u002Fisprs-archives.copernicus.org\u002Farticles\u002FXLII-2\u002F565\u002F2018\u002Fisprs-archives-XLII-2-565-2018.pdf) |Google Earth|1,6000| 256×256| 0.03-1m |-|2|\n|2018|BCD|河道| [The River Data Set](https:\u002F\u002Fshare.weiyun.com\u002F5xdge4R)|[TGRS2018](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8418840)|EO-1 Hyperion|1|463×241|30m|中国江苏|2|\n|2018|BCD|土地覆盖|[OSCD](https:\u002F\u002Fieee-dataport.org\u002Fopen-access\u002Foscd-onera-satellite-change-detection)|[IGARSS2018](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8518015)|Sentinel-2|24|600×600|10-60m|全球|2|\n|2008|BCD|土地覆盖|[SZTAKI](http:\u002F\u002Fweb.eee.sztaki.hu\u002Fremotesensing\u002Fairchange_benchmark.html)|[TGRS2009](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F5169964)|航空影像|13|952x640|1.5m|-|\n\n## 多模态与SAR数据集\n\n|年份|任务|目标| 数据集 |出版物|来源|图像对数 |图像尺寸|分辨率|地点|类别|\n|:---|:---|:--- | :------| :------|:----------| :-------| :-------| :----------- | :----- | :---- |\n|2025|DDA|灾害|[DisasterM3](https:\u002F\u002Fgithub.com\u002FJunjue-Wang\u002FDisasterM3)|[NeurIPS2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.21089)| 光学-SAR-指令 |-|-|-|全球|-|\n|2025|SCD|建筑物| [BRIGHT](https:\u002F\u002Fgithub.com\u002FChenHongruixuan\u002FBRIGHT) | [arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.06019) |光学与SAR|4,538| 1,024×1,024| 0.3-1m|全球|4|\n|2024|SCD|建筑物| [Hi-BCD](https:\u002F\u002Fgithub.com\u002FHATFormer\u002FMMCD) | [Information Fusion 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1566253524001362) |航拍图像、DSMs|1,500| 1,000×1,000 |0.25m |荷兰（阿姆斯特丹、鹿特丹和乌得勒支）|3|\n|2024|SCD|洪水 |[UrbanSARFloods](https:\u002F\u002Fgithub.com\u002Fjie666-6\u002FUrbanSARFloods)|[CVPR2024W](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2024W\u002FEarthVision\u002Fhtml\u002FZhao_UrbanSARFloods_Sentinel-1_SLC-Based_Benchmark_Dataset_for_Urban_and_Open-Area_Flood_CVPRW_2024_paper.html) | Sentinel-1|8,879| 512×512|20m|全球|5|\n|2024|SCD|土地利用 |[EVLab-CMCD](https:\u002F\u002Fgithub.com\u002Fwhudk\u002FEVLab-CMCD) | [ISPSR P&RS 2024](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271624003873)|GF-2, BJ-2, 历史土地利用图|5,622|512×512| 0.8m| 中国10个城市|13|\n|2023|BCD|洪水 |[CAU-Flood](https:\u002F\u002Fgithub.com\u002FCAU-HE\u002FCMCDNet)| [JAG2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1569843223000195) |Sentinel-1, Sentinel-2|18,302| 256×256|10m|全球|2|\n|2023|SCD|洪水|[Kuro Siwo](https:\u002F\u002Fgithub.com\u002FOrion-AI-Lab\u002FKuroSiwo)|[NeurIPS2024](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2024\u002Fhash\u002F43612b0662cb6a4986edf859fd6ebafe-Abstract-Datasets_and_Benchmarks_Track.html)|Sentinel-1, DEM| 67,490 |224×224| 10m|全球|3|\n|2023|SCD|城市|[SMARS](https:\u002F\u002Fwww.dlr.de\u002Fen\u002Feoc\u002Fabout-us\u002Fremote-sensing-technology-institute\u002Fphotogrammetry-and-image-analysis\u002Fpublic-datasets\u002Fsmars)| [ISPRS P&RS 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS092427162300254X)|模拟正射影像和DSMs|-|512×512|0.3m, 0.5m|模拟巴黎和威尼斯|3|\n|2023|BCD|城市|[3DCD](https:\u002F\u002Fsites.google.com\u002Funiroma1.it\u002F3dchangedetection\u002Fhome-page?pli=1) |[ISPRS P&RS 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271622003240)|航拍图像、DSMs|472|400×400, 200×200|0.5m, 1m|西班牙巴利亚多利德|2| \n|2023|SCD|城市|[Urb3DCD–V2](https:\u002F\u002Fieee-dataport.org\u002Fopen-access\u002Furb3dcd-urban-point-clouds-simulated-dataset-3d-change-detection)|[ISPRS P&RS 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271623000394)|ALS、多传感器|-|-|-|模拟|7|\n|2022|BCD|洪水| [武汉](https:\u002F\u002Fgithub.com\u002FGeoZcx\u002FA-Domain-Adaption-Neural-Network-for-Change-Detection-with-Heterogeneous-Optical-and-SAR-Remote-Sens\u002Ftree\u002Fmain\u002Fdata) | [JAG2022](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0303243422000952) |Sentinel-2, COSMO-SkyMed|1| 11,216×13,693|3m |武汉，中国|2|\n|2022|BCD|洪水|[Ombria](https:\u002F\u002Fgithub.com\u002Fgeodrak\u002FOMBRIA) |[JSTARS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9723593\u002F) |Sentinel-1, Sentinel-2| 1,688| 256×256| 10m|全球|2|\n|2021|BCD|土地覆盖|[MultiModalOSCD](https:\u002F\u002Fgithub.com\u002FPatrickTUM\u002FmultimodalCD_ISPRS21)|[ISPRS. XXIV ISPRS Congress 2021](https:\u002F\u002Fisprs-archives.copernicus.org\u002Farticles\u002FXLIII-B3-2021\u002F243\u002F2021\u002Fisprs-archives-XLIII-B3-2021-243-2021.pdf)|Sentinel-1, Sentinel-2|24|600×600|10-60m|全球|2|\n\n# 工具\n\n| 年份 | 缩写 | 描述 | 其他|\n| :--- | :--- | :--- | :--- |\n|2024|[rschange](https:\u002F\u002Fgithub.com\u002Fxwmaxwma\u002Frschange)|一个开源工具箱，专门用于复现和开发遥感图像变化检测的先进方法（如DDLNet、CDMask）。|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fxwmaxwma\u002Frschange.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fxwmaxwma\u002Frschange?style=social)|\n|2024|[torchange](https:\u002F\u002Fgithub.com\u002FZ-Zheng\u002Fpytorch-change-models)|一个基准库，提供开箱即用、直观的当代时空变化检测模型（如ChangeStar、Changen、AnyChange）、指标和数据集的实现，以促进遥感研究的可重复性。 |![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZ-Zheng\u002Fpytorch-change-models.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-Zheng\u002Fpytorch-change-models?style=social)|\n|2022| [Open-CD](https:\u002F\u002Fgithub.com\u002Flikyoo\u002Fopen-cd)|最全面的变化检测开源工具箱，提供统一平台，包含多种方法、训练\u002F推理工具、数据分析脚本和基准测试，以支持该领域的研究与开发。论文：[arXiv2024](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.15317)。 |![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flikyoo\u002Fopen-cd.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flikyoo\u002Fopen-cd?style=social)|\n|2022|[PaddleRS](https:\u002F\u002Fgithub.com\u002FPaddlePaddle\u002FPaddleRS)|基于PaddlePaddle的遥感工具包，支持包括变化检测在内的多项任务，提供专用模型（如BIT、FarSeg）、大图像处理能力以及分析时间序列土地覆盖差异的实用教程。其PyTorch版本称为[CDLab](https:\u002F\u002Fgithub.com\u002FBobholamovic\u002FCDLab)。|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FPaddlePaddle\u002FPaddleRS.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FPaddlePaddle\u002FPaddleRS?style=social)|\n|2020|[Change Detection Repository](https:\u002F\u002Fgithub.com\u002FChenHongruixuan\u002FChangeDetectionRepository)|它提供了精选传统变化检测方法（如CVA、SFA、MAD）和基于深度学习的方法（如SiamCRNN、DSFA以及基于FCN的方法）的Python实现。|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FChenHongruixuan\u002FChangeDetectionRepository.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FChenHongruixuan\u002FChangeDetectionRepository?style=social)|\n|2019|[ChangeDetectionToolbox](https:\u002F\u002Fgithub.com\u002FBobholamovic\u002FChangeDetectionToolbox)|这个MATLAB工具箱提供了一个模块化、端到端的遥感变化检测框架，实现了关键方法，如CVA、MAD和IRMAD，以生成差异图像并评估变化地图。|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FBobholamovic\u002FChangeDetectionToolbox.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FBobholamovic\u002FChangeDetectionToolbox?style=social)|\n\n\n# 方法\n\n## 深度学习\n\n### 基础模型\n\n| 年份 | 缩写 | 标题 | 发表期刊\u002F会议 | 基础模型 | 关键词 | 实验数据集 | 备注 |\n| :--- | :--- | :------| :--- | :--- | :--- |:------- |:------- |\n|2025|DaCDF|一种基于相对深度信息辅助的变化检测框架|[JAG2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1569843225005898?dgcid=rss_sd_all)|Depth Anything|Depth-Anything; 多任务学习|WHU-CD, LEVIR-CD, SECOND|-|\n|2025|[GeoVLM-R1](https:\u002F\u002Fgithub.com\u002Fmustansarfiaz\u002FGeoVLM-R1-Toolkit)|GeoVLM-R1：用于提升遥感推理能力的强化微调方法|[arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.25026)|Qwen2.5VL-3B-Instruct|任务感知奖励、基于推理的强化学习模型|GeoChat-Instruct, NWPU VHR-10; Dubai-CC, LEVIR-MCI, MUDS, SYSU-CD; NWPU-Captions, RSCID-Captions, RSITMD-Captions|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fmustansarfiaz\u002FGeoVLM-R1-Toolkit.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmustansarfiaz\u002FGeoVLM-R1-Toolkit?style=social)|\n|2025|ChangeVG|迈向遥感领域全面交互式变化理解：大规模数据集与双粒度增强的视觉语言模型|[arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.23105)|Qwen2.5-VL-7B|遥感变化理解、交互式多任务指令数据集、视觉语言模型|ChangeIMTI（由LEVIR-CC、LEVIR-MCI构建）|-|\n|2025|[SegChange-R1](https:\u002F\u002Fgithub.com\u002FYu-Zhouz\u002FSegChange-R1)|SegChange-R1：大语言模型增强的遥感变化检测方法|[arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.17944)|Swin Transformer, Microsoft\u002FPhi-1.5|大语言模型增强的推理方法、基于线性注意力的空间变换模块|WHU-CD, CDD, DSIFN-CD, DVCD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FYu-Zhouz\u002FSegChange-R1.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FYu-Zhouz\u002FSegChange-R1?style=social)|\n|2025|[SAM2-CD](https:\u002F\u002Fgithub.com\u002FKimotaQY\u002FSAM2-CD)|SAM2-CD：基于SAM2的遥感图像变化检测方法|[JSTAR2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11164661)|SAM2|动态特征选择、全局-局部注意力|WHU-CD, LEVIR-CD, 以及LEVIR-CD+|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FKimotaQY\u002FSAM2-CD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FKimotaQY\u002FSAM2-CD?style=social)|\n|2025|[ViTP](https:\u002F\u002Fgithub.com\u002Fzcablii\u002FViTP)|面向特定领域的基础模型的视觉指令预训练方法|[arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.17562)|ViT, InternVL-2.5|利用推理增强感知、ViT、视觉鲁棒性学习|16个具有挑战性的遥感和医学影像基准测试集|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fzcablii\u002FViTP.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzcablii\u002FViTP?style=social)|\n|2025|[AdaptVFMs-RSCD](https:\u002F\u002Fgithub.com\u002FJiang-CHD-YunNan\u002FRS-VFMs-Fine-tuning-Dataset)|AdaptVFMs-RSCD：利用SAM和CLIP将遥感变化检测从二值化推进到语义化|[ISPRS P&RS 2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271625003636?dgcid=rss_sd_all)|CLIP, SAM|遥感视觉基础模型微调数据集|遥感VFM微调数据集、DSIFN-CD、CLCD、SYSU-CD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FJiang-CHD-YunNan\u002FRS-VFMs-Fine-tuning-Dataset.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJiang-CHD-YunNan\u002FRS-VFMs-Fine-tuning-Dataset?style=social)|\n|2025|[PeftCD](https:\u002F\u002Fgithub.com\u002Fdyzy41\u002FPeftCD)|PeftCD：利用参数高效微调技术提升视觉基础模型在遥感变化检测中的性能|[arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.09572)|SAM2, DINOv3|视觉基础模型、参数高效微调|WHU-CD, CDD, LEVIR-CD, SYSU-CD, MSRSCD, MLCD, S2Looking|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fdyzy41\u002FPeftCD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdyzy41\u002FPeftCD?style=social)|\n|2025|DepthCD|平衡扩散引导的多模态遥感分类融合方法|[ISPRS P&RS 2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271625002072?dgcid=rss_sd_all)|ViT|深度提示、变化的维度相关性、轻量级适配器、二值化变化检测、语义化变化检测|SECOND, LandsatSCD, HiUCDs; SYSU-CD, HRCUS-CD, WRCD|-|\n|2025|[SA-CDNet](https:\u002F\u002Fgithub.com\u002FDREAMXFAR\u002FSA-CDNet)|像人类一样检测变化：结合语义先验提升变化检测性能|[TGRS2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11159523)|FastSAM|双流解码器、多尺度特征、视觉基础模型|AIRS、INRIA-Building和WHU-Building；DLCCC和LoveDA；WHU-CD、LEVIR-CD、LEVIR-CD+、S2Looking、WHU耕地数据集|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FDREAMXFAR\u002FSA-CDNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDREAMXFAR\u002FSA-CDNet?style=social)|\n| 2025 | [DynamicEarth](https:\u002F\u002Fgithub.com\u002Flikyoo\u002FDynamicEarth) | DynamicEarth：我们距离开放词汇变化检测还有多远？  | [arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.12931)|SAM2, DINOv2| 开放词汇变化检测| WHU-CD, LEVIR-CD, SECOND, S2Looking, 和 BANDON|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flikyoo\u002FDynamicEarth.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flikyoo\u002FDynamicEarth?style=social)|\n|2025|[DisasterM3](https:\u002F\u002Fgithub.com\u002FJunjue-Wang\u002FDisasterM3)|DisasterM3：用于灾害损毁评估与响应的遥感视觉语言数据集 | [NeurIPS2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.21089)|LLaVA, Kimi, InternVL, Qwen2.5, GeoCha, TeoChat, EarthDial, GPT4|多灾种、多传感器、多任务|DisasterM3|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FJunjue-Wang\u002FDisasterM3.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJunjue-Wang\u002FDisasterM3?style=social)|\n|2025|[EFI-SAM](https:\u002F\u002Fgithub.com\u002Fjuncyan\u002Fefi-sam)|基于SAM的遥感变化检测高效特征集成网络：以澳门填海为例|[JSTARS2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11058393\u002F)|SAM|随机傅里叶特征、填海工程|CLCD、SYSU-CD、S2Looking、MLCD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fjuncyan\u002Fefi-sam.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjuncyan\u002Fefi-sam?style=social)|\n| 2024 | [AnyChange](https:\u002F\u002Fgithub.com\u002FZ-Zheng\u002Fpytorch-change-models\u002Fblob\u002Fmain\u002Ftorchange\u002Fmodels\u002Fsegment_any_change) | 分割任意变化 | [NeurIPS2024](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper_files\u002Fpaper\u002F2024\u002Ffile\u002F9415416201aa201902d1743c7e65787b-Paper-Conference.pdf) | SAM| 零样本变化检测、双时相潜在匹配|xBD, LEVIR-CD, S2Looking, SECOND  | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZ-Zheng\u002Fpytorch-change-models.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-Zheng\u002Fpytorch-change-models?style=social) |\n|2024|[SCM](https:\u002F\u002Fgithub.com\u002FStephenApX\u002FUCD-SCM)|无监督遥感高分辨率图像变化检测的分割变化模型（SCM）：以建筑物为例|[IGARSS 2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10642429)|SAM, CLIP|无监督变化检测、视觉基础模型|WHU-CD, LEVIR-CD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FStephenApX\u002FUCD-SCM.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FStephenApX\u002FUCD-SCM?style=social) |\n|2024|[SemiCD-VL](https:\u002F\u002Fgithub.com\u002Flikyoo\u002FSemiCD-VL) |SemiCD-VL：视觉语言模型指导下的半监督变化检测器更优| [TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10781418) |APE |视觉语言模型、半监督学习、基础模型|WHU-CD, LEVIR-CD| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flikyoo\u002FSemiCD-VL.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flikyoo\u002FSemiCD-VL?style=social) |\n|2024|[ChangeCLIP](https:\u002F\u002Fgithub.com\u002Fdyzy41\u002FChangeCLIP) | ChangeCLIP：基于多模态视觉语言表征学习的遥感变化检测方法 | [ISPRS P&RS 2024](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271624000042) |CLIP| 多模态、视觉语言表征学习 |WHU-CD, CDD, LEVIR-CD, LEVIR-CD+，以及SYSU-CD| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fdyzy41\u002FChangeCLIP.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fdyzy41\u002FChangeCLIP?style=social) |\n| 2023 | [BAN](https:\u002F\u002Fgithub.com\u002Flikyoo\u002FBAN) | 基于基础模型的遥感变化检测新学习范式 | [TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F10438490\u002F) |CLIP| 基础模型、视觉调优 | WHU-CD, LEVIR-CD, S2Looking, Landsat-SCD, 以及 BANDON| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flikyoo\u002FBAN.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flikyoo\u002FBAN?style=social) |\n| 2023 | [SAM-CD](https:\u002F\u002Fgithub.com\u002FggsDing\u002FSAM-CD) | 将Segment Anything Model应用于遥感高分辨率图像的变化检测 | [TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10443350)| SAM |视觉基础模型 | WHU-CD, LEVIR-CD, CLCD, S2Looking| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FggsDing\u002FSAM-CD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FggsDing\u002FSAM-CD?style=social) |\n\n### 扩散模型与GAN\n\n| 年份 | 缩写 | 标题 | 发表刊物 | 关键词 | 实验数据集 | 其他      |\n| :--- | :--- | :--- | :--- | :--- | :--- |:--- |\n|2025|[CT2Net](https:\u002F\u002Fgithub.com\u002FJiahuiqu\u002FCT2Net)|基于循环翻译的协同训练用于高光谱-RGB多模态变化检测|[TPAMI2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11164958)|CycleGAN, 高光谱-RGB图像, 多模态变化检测, 图像翻译, 协同训练|湾区（HSI-RGB）、圣巴巴拉（HSI-RGB）、赫米斯顿（HSI-RGB）、XDU-李峪口（HSI-RGB）|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FJiahuiqu\u002FCT2Net.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJiahuiqu\u002FCT2Net?style=social)|\n|2025|[NeDS](https:\u002F\u002Fgithub.com\u002FZ-Zheng\u002Fpytorch-change-models)|用于可迁移建筑物损伤评估的神经灾害模拟|[RSE2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425725003839?dgcid=rss_sd_all)|合成数据微调, 深度生成模型, 条件潜扩散模型|xBD、洛杉矶野火（2025年）和尼日利亚洪水（2025年）|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZ-Zheng\u002Fpytorch-change-models.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-Zheng\u002Fpytorch-change-models?style=social)|\n|2025|[BDGF](https:\u002F\u002Fgithub.com\u002FHaoLiu-XDU\u002FBDGF)|用于多模态遥感分类的平衡扩散引导融合|[arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.23310)|去噪扩散概率模型, 自适应模态掩码策略, 互学习策略|柏林数据集（HSI+SAR）、奥格斯堡数据集（HSI+SAR）、黄河口数据集（HSI+SAR）、LCZ HK数据集（MSI+SAR）|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FHaoLiu-XDU\u002FBDGF.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHaoLiu-XDU\u002FBDGF?style=social)|\n|2025|[RS-NormGAN](https:\u002F\u002Fgithub.com\u002Flixinghua5540\u002FRS-NormGAN)|RS-NormGAN：通过有效辐射归一化提升多时相光学遥感图像的变化检测|ISPRS P&RS 2025|深度风格迁移；领域适应；GAN；多时相辐射归一化|GESD、SHCD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flixinghua5540\u002FRS-NormGAN.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flixinghua5540\u002FRS-NormGAN?style=social)|\n|2024|[UP-Diff](https:\u002F\u002Fgithub.com\u002Fzeyuwang-zju\u002FUP-Diff)|UP-Diff：用于遥感城市预测的潜扩散模型|[GRSL2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10807291)|交叉注意力, 潜扩散模型, 城市规划|LEVIR-CD、SYSU-CD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fzeyuwang-zju\u002FUP-Diff.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzeyuwang-zju\u002FUP-Diff?style=social)|\n|2024|[ChangeDiff](https:\u002F\u002Fgithub.com\u002FDZhaoXd\u002FChangeDiff)|ChangeDiff：基于扩散模型的灵活文本提示多时相变化检测数据生成器|[AAAI2025](https:\u002F\u002Fojs.aaai.org\u002Findex.php\u002FAAAI\u002Farticle\u002Fview\u002F33058)|扩散模型, 文本到布局模型, 多类别分布引导的文本提示|SECOND、Landsat-SCD和HRSCD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FDZhaoXd\u002FChangeDiff.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FDZhaoXd\u002FChangeDiff?style=social)|\n| 2024 | [Changen2](https:\u002F\u002Fgithub.com\u002FZ-Zheng\u002Fpytorch-change-models\u002Ftree\u002Fmain\u002Ftorchange\u002Fmodels\u002Fchangen2) | Changen2：多时相遥感生成式变化基础模型 | [TPAMI2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10713915\u002F) | 合成数据预训练, 生成模型, 基础模型 | WHU-CD、xBD、LEVIR-CD、S2Looking、SECOND| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZ-Zheng\u002Fpytorch-change-models.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-Zheng\u002Fpytorch-change-models?style=social) |\n| 2023 | [Changen](https:\u002F\u002Fgithub.com\u002FZ-Zheng\u002FChangen) | 通过模拟随机变化过程实现可扩展的多时相遥感变化数据生成 | [ICCV2023](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FICCV2023\u002Fpapers\u002FZheng_Scalable_Multi-Temporal_Remote_Sensing_Change_Data_Generation_via_Simulating_Stochastic_ICCV_2023_paper.pdf) | 深度生成模型, 变化事件模拟, 语义变化合成 | WHU-CD、LEVIR-CD、S2Looking| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZ-Zheng\u002FChangen.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-Zheng\u002FChangen?style=social) |\n| 2022 | [DDPM-CD](https:\u002F\u002Fgithub.com\u002Fwgcban\u002Fddpm-cd) | DDPM-CD：作为特征提取器的去噪扩散概率模型用于遥感变化检测| [WACV2025](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FWACV2025\u002Fpapers\u002FBandara_DDPM-CD_Denoising_Diffusion_Probabilistic_Models_as_Feature_Extractors_for_Remote_WACV_2025_paper.pdf) | 图像合成, 去噪扩散概率模型 | WHU-CD、CDD、DSIFN-CD和LEVIR-CD | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fwgcban\u002Fddpm-cd.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwgcban\u002Fddpm-cd?style=social) |\n\n\n### 变压器\n\n| 年份 | 缩写 | 标题 | 发表刊物 | 关键词 | 实验数据集 | 其他 |\n| :--- | :--- | :--- | :--- | :--- | :--- |:--- |\n|2025|[BTC](https:\u002F\u002Fgithub.com\u002Fblaz-r\u002FBTC-change-detection)|成为你希望看到的改变：重新审视遥感变化检测实践|[TGRS2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11063303)|变化检测、方法优化、遥感、监督学习|SYSU-CD、LEVIR-CD、EGY-BCD、GVLM-CD、CLCD、OSCD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fblaz-r\u002FBTC-change-detection.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fblaz-r\u002FBTC-change-detection?style=social)|\n|2025|[CMNet](https:\u002F\u002Fgithub.com\u002FJscript10\u002FCMNet)|CMNet：一种具有相似性导向和差异感知的CNN–Mamba网络用于变化检测|[TGRS2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11208164\u002F)|差异感知、相似性导向、CNN–Mamba|DSIFN-CD、LEVIR-CD、SYSU-CD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FJscript10\u002FCMNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJscript10\u002FCMNet?style=social)|\n|2025|[MBUKG_DCKRL_CD](https:\u002F\u002Ffigshare.com\u002Farticles\u002Fonline_resource\u002FMBUKG_DCKRL_CD\u002F27897873)|一种基于多模态数据和知识图谱技术的城市变化检测方法|[IJDE2025](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F17538947.2025.2564902?af=R)|城市变化检测、多模态知识图谱、多源数据表示学习、双交叉注意力机制|包含VHR影像、POI数据和SVI的综合数据集|-|\n|2025|[S-cCDNet](https:\u002F\u002Fgithub.com\u002FShelly-H\u002FS-cCDNet)|以语义为中心的变化检测框架：考虑土地覆盖的时空异质性和时空相关性|[IJDE2025](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F17538947.2025.2569406?af=R)|多任务学习、原型表示、时空异质性、时空相关性|SECOND、Landsat-SCD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FShelly-H\u002FS-cCDNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FShelly-H\u002FS-cCDNet?style=social)|\n|2025|[CPGNet](https:\u002F\u002Fgithub.com\u002Flong123524\u002FCPGNet)|通过整合语义关联和变化先验，从VHR遥感图像中检测语义变化|[JAG2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1569843225005631?dgcid=rss_sd_all)|语义关联；多视角；变化先验引导网络|JL1；厦门（XM）耕地非农化数据集；SECOND|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flong123524\u002FCPGNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flong123524\u002FCPGNet?style=social)|\n|2025|[FoBa](https:\u002F\u002Fgithub.com\u002Fzmoka-zht\u002FFoBa)|FoBa：一种前景-背景协同引导的方法及遥感语义变化检测的新基准|[arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.15788)|前景背景协同引导、双时相交互、mamba、新基准|SECOND、JL1以及提出的LevirSCD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fzmoka-zht\u002FFoBa.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzmoka-zht\u002FFoBa?style=social)|\n|2025|[GSTM-SCD](https:\u002F\u002Fgithub.com\u002Fliuxuanguang\u002FGSTM-SCD)|GSTM-SCD：用于多时相遥感图像语义变化检测的图增强时空状态空间模型|[ISPRS P&RS 2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271625003557?dgcid=rss_sd_all)|状态空间模型、图优化、时空建模|SECOND、Landsat-SCD、WUSU和DynamicEarthNet|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fliuxuanguang\u002FGSTM-SCD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fliuxuanguang\u002FGSTM-SCD?style=social)|\n|2025|[Change3D](https:\u002F\u002Fgithub.com\u002Fzhuduowang\u002FChange3D)|Change3D：从视频建模视角重新审视变化检测与字幕生成|[CVPR2025](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2025\u002Fhtml\u002FZhu_Change3D_Revisiting_Change_Detection_and_Captioning_from_A_Video_Modeling_CVPR_2025_paper.html)|感知特征提取、变化解码器、字幕解码器|WHU-CD、HRSCD、xBD、LEVIR-CD、CLCD、SECOND、LEVIR-CC和DUBAI-CC|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fzhuduowang\u002FChange3D.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzhuduowang\u002FChange3D?style=social)|\n| 2025 |[UA-BCD](https:\u002F\u002Fgithub.com\u002FHenryjiepanli\u002FUA-BCD)|克服从遥感图像中检测建筑物变化的不确定性挑战| [ISPRS P&RS 2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS092427162400426X)|不确定性相关理论、建筑物变化检测映射、暹罗金字塔视觉变换器|CDD、WHU-CD、GZ-CD、LEVIR-CD、SYSU-CD| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FHenryjiepanli\u002FUA-BCD.svg?style=flat&logo=github&label=Last%20Commit) ![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHenryjiepanli\u002FUA-BCD?style=social)|\n|2025|[SMGNet](https:\u002F\u002Fgithub.com\u002Flong123524\u002FSMGNet)|SMGNet：一种语义地图引导的多任务神经网络，用于遥感图像语义变化检测|[GRSL2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11023838)|历史语义信息、伪变化、语义地图引导网络、漏检|HRSCD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flong123524\u002FSMGNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flong123524\u002FSMGNet?style=social)|\n|2024|[HGINet](https:\u002F\u002Fgithub.com\u002Flong123524\u002FHGINet-torch)|利用层次化语义图交互网络从高分辨率遥感图像中进行语义变化检测|[ISPRS P&RS 2024](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271624001709)|层次化语义图交互网络；时间相关性；语义差异交互|SECOND、HRSCD、福州和厦门|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flong123524\u002FHGINet-torch.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flong123524\u002FHGINet-torch?style=social)|\n| 2024 |STCA| 通过无监督单时相变化适应实现可迁移的建筑损伤评估 | [RSE2024](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425724004425?dgcid=rss_sd_all) | 无监督适应、单时相学习、语义变化检测 | xBD、土耳其–叙利亚地震（2023年）、刚果民主共和国卡莱赫洪灾（2023年）、夏威夷茂宜岛火灾（2023年） | - |\n| 2024 | [ChangeSparse](https:\u002F\u002Fgithub.com\u002FZ-Zheng\u002Fpytorch-change-models\u002Fblob\u002Fmain\u002Ftorchange\u002Fmodels\u002Fchangesparse.py) | 通过深度概率变化模型统一遥感变化检测：从原理、模型到应用 | [ISPRS P&RS 2024](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271624002624) | 概率变化模型、变化稀疏性、稀疏变化Transformer | CDD、S2Looking、加州洪水数据集、xBD、SECOND、DynamicEarthNet | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZ-Zheng\u002Fpytorch-change-models.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-Zheng\u002Fpytorch-change-models?style=social) |\n| 2024 | [ChangeStar2](https:\u002F\u002Fgithub.com\u002FZ-Zheng\u002Fpytorch-change-models\u002Fblob\u002Fmain\u002Ftorchange\u002Fmodels\u002Fchangestar2.py) | 单时相监督学习用于通用遥感变化检测 | [IJCV2024](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs11263-024-02141-4) | 通用变化检测、单时相监督学习 |WHU-CD、CDD、xBD、LEVIR-CD、S2Looking、SpaceNet8、DynamicEarthNet、SECOND| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZ-Zheng\u002Fpytorch-change-models.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-Zheng\u002Fpytorch-change-models?style=social) |\n| 2024 | [BiFA](https:\u002F\u002Fgithub.com\u002Fzmoka-zht\u002FBiFA) | BiFA：具有双时相特征对齐的遥感图像变化检测 | [TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10471555) | 双时相交互、特征对齐、流场|WHU-CD、LEVIR-CD、LEVIR-CD+、SYSU-CD、DSIFN-CD和CLCD| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fzmoka-zht\u002FBiFA.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzmoka-zht\u002FBiFA?style=social)|\n| 2024 | [CDMamba](https:\u002F\u002Fgithub.com\u002Fzmoka-zht\u002FCDMamba) | CDMamba：将局部线索融入Mamba用于遥感图像二值变化检测 | [TGRS2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10902569) | Mamba、双时相交互、状态空间模型|WHU-CD、CDD、LEVIR-CD、LEVIR-CD+和CLCD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fzmoka-zht\u002FCDMamba.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fzmoka-zht\u002FCDMamba?style=social) |\n| 2024 | [CDMask](https:\u002F\u002Fgithub.com\u002Fxwmaxwma\u002Frschange) | 以掩膜视角重新思考遥感变化检测 | [arXiv2024](https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.15320) | 掩膜视角、掩膜级别分类、MaskFormer|WHU-CD、LEVIR-CD、SYSU-CD、DSIFN-CD和CLCD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fxwmaxwma\u002Frschange.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fxwmaxwma\u002Frschange?style=social)|\n| 2024 | [ChangeMamba](https:\u002F\u002Fgithub.com\u002FChenHongruixuan\u002FChangeMamba) | ChangeMamba：具有时空状态空间模型的遥感变化检测 | [TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10565926) | Mamba、时空关系、状态空间模型|WHU-CD、xBD、SECOND、LEVIR-CD+和SYSU-CD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FChenHongruixuan\u002FChangeMamba.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FChenHongruixuan\u002FChangeMamba?style=social) |\n| 2024 | [MaskCD](https:\u002F\u002Fgithub.com\u002FAI4RS\u002FMaskCD) | MaskCD：一种基于掩膜分类的遥感变化检测网络 | [TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10587034) | 可变形注意力、掩膜分类、掩膜交叉注意力|LEVIR-CD、CLCD、SYSU-CD、EGY-BCD和GVLM-CD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FAI4RS\u002FMaskCD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAI4RS\u002FMaskCD?style=social) |\n| 2024 | [M-CD](https:\u002F\u002Fgithub.com\u002FJayParanjape\u002FM-CD) | 一种基于Mamba的暹罗网络用于遥感变化检测 | [arXiv2024](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.06839) | Mamba、状态空间模型、差异模块| WHU-CD、CDD、DSIFN-CD和LEVIR-CD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FJayParanjape\u002FM-CD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FJayParanjape\u002FM-CD?style=social) |\n| 2024 | [ScratchFormer](https:\u002F\u002Fgithub.com\u002Fmustansarfiaz\u002FScratchFormer) | 从头训练的Transformer用于遥感变化检测 | [TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10489990) | 从头训练、打乱的稀疏注意力操作、变化增强特征融合、 | WHU-CD、OSCD、CDD、DSIFN-CD和LEVIR-CD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fmustansarfiaz\u002FScratchFormer.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmustansarfiaz\u002FScratchFormer?style=social) |\n| 2024 | [SitsSCD](https:\u002F\u002Fgithub.com\u002FElliotVincent\u002FSitsSCD) | 卫星影像时间序列语义变化检测：新颖架构及领域偏移分析 | [arXiv2024](https:\u002F\u002Farxiv.org\u002Fabs\u002F2407.07616)| 时间注意力、时间偏移、空间偏移| DynamicEarthNet、MUDS|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FElliotVincent\u002FSitsSCD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FElliotVincent\u002FSitsSCD?style=social) |\n| 2023 | [3DCD](https:\u002F\u002Fgithub.com\u002FVMarsocci\u002F3DCD) | 从双时相光学图像推断3D变化检测 | [ISPRS P&RS 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271622003240) | 3D变化检测、高程变化检测 | 3DCD | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FVMarsocci\u002F3DCD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FVMarsocci\u002F3DCD?style=social) |\n| 2023 | [Siamese KPConv](https:\u002F\u002Fgithub.com\u002FIdeGelis\u002Ftorch-points3d-SiameseKPConv) | Siamese KPConv：使用深度学习从原始点云中进行多对象变化检测 | [ISPRS P&RS 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271623000394?via%3Dihub) | 3D变化检测、暹罗网络、3D Kernel Point Convolution | Urb3DCD–V2、AHN-CD、Change3D | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FIdeGelis\u002Ftorch-points3d-SiameseKPConv.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FIdeGelis\u002Ftorch-points3d-SiameseKPConv?style=social) |\n| 2023 | [MapFormer](https:\u002F\u002Fgithub.com\u002Fmxbh\u002Fmapformer) | MapFormer：利用变化前信息提升变化检测 | [ICCV2023](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FICCV2023\u002Fpapers\u002FBernhard_MapFormer_Boosting_Change_Detection_by_Using_Pre-change_Information_ICCV_2023_paper.pdf) | 条件变化检测、多模态特征融合、跨模态对比损失|HRSCD、DynamicEarthNet   | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fmxbh\u002Fmapformer.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmxbh\u002Fmapformer?style=social) |\n| 2023 | [CACo](https:\u002F\u002Fgithub.com\u002Futkarshmall13\u002Fcaco) | 面向卫星图像的变化感知采样和对比学习 | [CVPR2023](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2023\u002Fpapers\u002FMall_Change-Aware_Sampling_and_Contrastive_Learning_for_Satellite_Images_CVPR_2023_paper.pdf) | 自监督学习、变化感知对比损失| OSCD、DynamicEarthNet、EuroSat和BigEarthNet| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Futkarshmall13\u002Fcaco.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Futkarshmall13\u002Fcaco?style=social) |\n| 2023 | [Self-Pair](https:\u002F\u002Fgithub.com\u002Fseominseok0429\u002FSelf-Pair-for-Change-Detection) | Self-Pair：从单一来源合成变化，用于遥感影像中的目标变化检测 | [WACV2023](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FWACV2023\u002Fpapers\u002FSeo_Self-Pair_Synthesizing_Changes_From_Single_Source_for_Object_Change_Detection_WACV_2023_paper.pdf) | 合成数据、单时相监督、未变化区域的视觉相似性 | WHU-CD、SpaceNet2、xBD、LEVIR-CD | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fseominseok0429\u002FSelf-Pair-for-Change-Detection.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fseominseok0429\u002FSelf-Pair-for-Change-Detection?style=social) |\n| 2022 | [Changer](https:\u002F\u002Fgithub.com\u002Flikyoo\u002Fopen-cd\u002Ftree\u002Fmain\u002Fconfigs\u002Fchanger) | Changer：特征交互是变化检测所需的关键 | [TGRS2023](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10129139) | 脚本交互 | LEVIR-CD、S2Looking | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flikyoo\u002Fopen-cd.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flikyoo\u002Fopen-cd?style=social) |\n| 2022 | [ChangeMask](https:\u002F\u002Fgithub.com\u002FZ-Zheng\u002Fpytorch-change-models\u002Fblob\u002Fmain\u002Ftorchange\u002Fmodels\u002Fchangemask.py) | ChangeMask：用于语义变化检测的深层多任务编码器-Transformer-解码器架构 | [ISPRS P&RS 2022](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271621002835) | 多任务学习、时间对称性、多时相|SECOND、Hi-UCD| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZ-Zheng\u002Fpytorch-change-models.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-Zheng\u002Fpytorch-change-models?style=social) |\n| 2022 | [FHD](https:\u002F\u002Fgithub.com\u002FZSVOS\u002FFHD) | 用于遥感图像变化检测的特征层次差异化 | [GRSL2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9837915) | 层次差异化、特定时间特征| DSIFN、LEVIR-CD、LEVIR-CD+、S2Looking | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZSVOS\u002FFHD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZSVOS\u002FFHD?style=social) |\n| 2022 | [SST-Former](https:\u002F\u002Fgithub.com\u002Fyanhengwang-heu\u002FIEEE_TGRS_SSTFormer) | 用于高光谱图像变化检测的光谱–空间–时间Transformer | [TGRS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9870837) | 高光谱、交叉注意力、自注意力 | 农田CD数据集、芭芭拉CD数据集和湾区CD数据集  | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fyanhengwang-heu\u002FIEEE_TGRS_SSTFormer.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyanhengwang-heu\u002FIEEE_TGRS_SSTFormer?style=social) |\n| 2022 | [CDViT](https:\u002F\u002Fgithub.com\u002Fshinianzhihou\u002FChangeDetection) | 一种用于遥感变化检测的分割式时空上下文网络 | [JSTARS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9779962) | 自注意力、时空Transformer | WHU-CD、LEVIR-CD | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fshinianzhihou\u002FChangeDetection.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fshinianzhihou\u002FChangeDetection?style=social) |\n| 2022 | [ChangeFormer](https:\u002F\u002Fgithub.com\u002Fwgcban\u002FChangeFormer) | 一种基于Transformer的暹罗网络用于变化检测 | [IGARSS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9883686) | Transformer暹罗网络、注意力机制| DSIFN-CD和LEVIR-CD| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fwgcban\u002FChangeFormer.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwgcban\u002FChangeFormer?style=social) |\n| 2021 | [BIT](https:\u002F\u002Fgithub.com\u002Fjustchenhao\u002FBIT_CD) | 使用Transformer进行遥感图像变化检测 | [TGRS2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9491802) | Transformer | WHU-CD、DSIFN-CD、LEVIR-CD | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fjustchenhao\u002FBIT_CD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjustchenhao\u002FBIT_CD?style=social) |\n\n### 卷积神经网络\n\n| 年份 | 缩写 | 标题 | 发表刊物 | 关键词 | 实验数据集 | 其他 |\n| :--- | :--- | :--- | :--- | :--- | :--- |:--- |\n|2025|[RACDNet](https:\u002F\u002Fgithub.com\u002FLYT-max\u002FRACDNet)|基于空频双域学习的任意分辨率遥感变化检测|[ISPRS P&RS 2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271625004113?dgcid=rss_sd_all)|任意分辨率变化检测；梯度先验；双域学习|WHU-CD、LEVIR-CD、SYSU-CD及Google数据集|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FLYT-max\u002FRACDNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLYT-max\u002FRACDNet?style=social)|\n|2025|[RIEM](https:\u002F\u002Fgithub.com\u002Fyulisun\u002FRIEM)|无需图像对比的变化检测：异构遥感影像中的规则诱导变化检测|[ISPRS P&RS 2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271625003612?dgcid=rss_sd_all)|异构数据、多模态、基于能量的模型|多源数据|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fyulisun\u002FRIEM.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fyulisun\u002FRIEM?style=social)|\n|2025|[Semantic-TemporalNet](https:\u002F\u002Fgithub.com\u002FCUG-BEODL\u002FSTN)|语义-时序网络：一种基于语义一致性分析的城市街区变化检测新方法|[TGRS2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11172373)|哨兵-2、时间序列语义一致性、城市更新|长沙和武汉的哨兵-2影像|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FCUG-BEODL\u002FSTN.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FCUG-BEODL\u002FSTN?style=social)|\n|2025|[TripleS](https:\u002F\u002Fgithub.com\u002FStephenApX\u002FMTL-TripleS)|TripleS：缓解高分辨率遥感影像中语义变化检测的多任务学习冲突|[ISPRS P&RS 2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271625003776?dgcid=rss_sd_all)|多任务学习、土地覆盖与土地利用|HRSCD、SC-SCD7、CC-SCD5|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FStephenApX\u002FMTL-TripleS.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FStephenApX\u002FMTL-TripleS?style=social)|\n| 2025 | CDFNet | 跨场景受损建筑物提取网络：基于单时相高分辨率遥感影像的方法、应用与效率 | [ISPRS P&RS2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271625002540?dgcid=rss_sd_all) | 建筑物损毁提取、跨场景、单时相、特征分解 | 云南和哈维灾后受损建筑物数据集，一个辅助数据集（两个地震多发区、一个洪水多发区、四个非灾区），一个应用测试数据集（八个涵盖火山、地震、海啸、野火和飓风场景的异质区域） |-|\n|2025|[PRO-HRSCD](https:\u002F\u002Fgithub.com\u002Fsdust-mmlab\u002FPRO-HRSCD)|从语义对齐视角重新思考语义变化检测|[TGRS2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F11162709\u002F)|特征空间对齐、多任务学习、原型学习|SECOND和Landsat-SCD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fsdust-mmlab\u002FPRO-HRSCD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsdust-mmlab\u002FPRO-HRSCD?style=social)|\n|2025|H-FIENet|利用多源卫星影像进行洪涝淹没监测：一种用于异构影像变化检测的知识迁移策略|[RSE2024](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425724003997)|洪涝制图、多源影像、跨任务转换|高分二号、高分三号、哨兵-1和哨兵-2|-|\n|2024|[STMNet](https:\u002F\u002Fgithub.com\u002FZhoutya\u002FChangeDetection-STMNet)|STMNet：基于单时相掩膜的自监督高光谱变化检测网络|[TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10817647)|高光谱影像、多尺度特征、单时相、掩膜|农田数据集、赫米斯顿数据集、贝伊数据集|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZhoutya\u002FChangeDetection-STMNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZhoutya\u002FChangeDetection-STMNet?style=social)|\n|2024|[ClearSCD](https:\u002F\u002Fgithub.com\u002Ftangkai-RS\u002FClearSCD)|ClearSCD模型：全面利用语义与变化关系进行高空间分辨率遥感影像的语义变化检测|[ISPRS P&RS 2024](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271624001734)|多任务学习、对比学习、变化矢量分析|Hi-UCD、LsSCD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Ftangkai-RS\u002FClearSCD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftangkai-RS\u002FClearSCD?style=social)|\n| 2024 | [SSLChange](https:\u002F\u002Fgithub.com\u002FMarsZhaoYT\u002FSSLChange)| SSLChange：基于领域适应的自监督变化检测框架| [TGRS2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10741199)| 领域适应、层次化特征、图像对比学习|CDD、LEVIR-CD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FMarsZhaoYT\u002FSSLChange.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FMarsZhaoYT\u002FSSLChange?style=social)|\n|2024|[U-Net、U-Net SiamDiff和U-Net SiamConc](https:\u002F\u002Fgithub.com\u002Fisaaccorley\u002Fa-change-detection-reality-check) | 变化检测现实检验 | [ICLR2024W](https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.06994) | 现实检验、基准测试 |WHU-CD、LEVIR-CD| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fisaaccorley\u002Fa-change-detection-reality-check.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fisaaccorley\u002Fa-change-detection-reality-check?style=social)|\n|2024|CCNet|和谐共生：超高分辨率遥感影像的内容净化变化检测框架|[ISPRS P&RS 2024](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS092427162400340X)|特征解耦、内容净化、图像修复|CDD、LEVIR-CD、xBD、SECOND、SYSU-CD、多时相xBD|-|\n| 2023 | [I3PE](https:\u002F\u002Fgithub.com\u002FChenHongruixuan\u002FI3PE) | 交换即变化：基于图像内和图像间补丁交换的无监督单时相变化检测框架 | [ISPRS P&RS 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS092427162300309X) | 单时相变化检测、图像补丁交换、自适应聚类 | SYSU-CD、SECOND、武汉数据集| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FChenHongruixuan\u002FI3PE.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FChenHongruixuan\u002FI3PE?style=social) |\n| 2023 | [A2Net](https:\u002F\u002Fgithub.com\u002Fguanyuezhen\u002FA2Net) | 基于渐进式特征聚合与监督注意力的轻量化遥感变化检测 | [TGRS2023](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10034814) | 轻量化、渐进式特征聚合、监督注意力 |WHU-CD、LEVIR-CD和SYSU-CD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fguanyuezhen\u002FA2Net.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fguanyuezhen\u002FA2Net?style=social)|\n| 2023 | [DMINet](https:\u002F\u002Fgithub.com\u002FZhengJianwei2\u002FDMINet) | 基于双分支多级时序网络的遥感影像变化检测 | [TGRS2023](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10034787) | 双分支差异获取、时序联合注意力、多级聚合|WHU-CD、GZ-CD、LEVIR-CD和SYSU-CD|![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZhengJianwei2\u002FDMINet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZhengJianwei2\u002FDMINet?style=social)|\n| 2023 | [AFCF3D-Net](https:\u002F\u002Fgithub.com\u002Fwm-Githuber\u002FAFCF3D-Net) | 基于3D CNN的相邻层级特征交叉融合用于遥感影像变化检测 | [TGRS2023](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10221754) | 3D CNN、特征交叉融合、全尺度连接|WHU-CD、LEVIR-CD、SYSU-CD| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fwm-Githuber\u002FAFCF3D-Net.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwm-Githuber\u002FAFCF3D-Net?style=social)|\n| 2023 | [LightCDNet](https:\u002F\u002Fgithub.com\u002FNightSongs\u002FLightCDNet) | LightCDNet：基于VHR影像的轻量化变化检测网络 | [GRSL2023](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10214556) | 早期融合、轻量化、深度监督融合|LEVIR-CD| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FNightSongs\u002FLightCDNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FNightSongs\u002FLightCDNet?style=social)|\n| 2023 | [USSFC-Net](https:\u002F\u002Fgithub.com\u002FSUST-reynole\u002FUSSFC-Net) | 超轻量级时空特征协作网络用于遥感影像变化检测 | [TGRS2023](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10081023) | 超轻量级、多尺度特征提取、时空特征协作| CDD、DSIFN-CD、LEVIR-CD | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FSUST-reynole\u002FUSSFC-Net.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSUST-reynole\u002FUSSFC-Net?style=social)|\n| 2023 | [SAR-CD](https:\u002F\u002Fgithub.com\u002Fjanne-alatalo\u002Fsar-change-detection) | 利用深度学习改进SAR影像中变化检测分类器的差分图像 | [TGRS2023](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10286479) | 映射变换函数、SAR、U-Net| SCDD | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fjanne-alatalo\u002Fsar-change-detection.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjanne-alatalo\u002Fsar-change-detection?style=social)|\n| 2022 | [RDPNet](https:\u002F\u002Fgithub.com\u002FChnja\u002FRDPNet) | RDP-Net：用于变化检测的区域细节保持网络 | [TGRS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9970750) | 训练策略、边缘损失、轻量化骨干 | CDD、LEVIR-CD | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FChnja\u002FRDPNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FChnja\u002FRDPNet?style=social)|\n| 2022 | [FFCTL](https:\u002F\u002Fgithub.com\u002Flauraset\u002FFFCTL) | 一种全层次融合的跨任务迁移学习方法，用于基于众包标签的噪声鲁棒预训练网络进行建筑物变化检测 | [RSE2022](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425722004771) | 迁移学习、众包标签、伪标签 | ZY-3建筑与变化检测数据集 | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flauraset\u002FFFCTL.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flauraset\u002FFFCTL?style=social)|\n| 2022 | [SaDL_CD](https:\u002F\u002Fgithub.com\u002Fjustchenhao\u002FSaDL_CD) | 语义感知的密集表示学习用于遥感影像变化检测 | [TGRS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9721305) | 自监督学习、语义感知表示学习| WHU-CD、GZ-CD、LEVIR-CD | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fjustchenhao\u002FSaDL_CD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjustchenhao\u002FSaDL_CD?style=social)|\n| 2022 | [TinyCD](https:\u002F\u002Fgithub.com\u002FAndreaCodegoni\u002FTiny_model_4_CD) | TINYCD：一个（并不那么）深度的学习模型用于变化检测 | [Neural Comput & Applic 2022](https:\u002F\u002Fgithub.com\u002FAndreaCodegoni\u002FTiny_model_4_CD) | 轻量化、小型模型、暹罗U-Net架构、特征交互 | WHU-CD、LEVIR-CD | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FAndreaCodegoni\u002FTiny_model_4_CD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAndreaCodegoni\u002FTiny_model_4_CD?style=social)|\n| 2022 | [SDACD](https:\u002F\u002Fgithub.com\u002FPerfect-You\u002FSDACD) | 一个端到端的监督领域适应框架用于跨领域变化检测 | [PR2022](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS003132032200440X) | 监督领域适应、图像适应、特征适应 |CDD和WHU-CD | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FPerfect-You\u002FSDACD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FPerfect-You\u002FSDACD?style=social)|\n| 2022 | [Bi-SRNet](https:\u002F\u002Fgithub.com\u002FggsDing\u002FBi-SRNet) | 高分辨率遥感影像中语义变化检测的双时相语义推理 | [TGRS2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9721305) | 三分支、语义关联| SECOND| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FggsDing\u002FBi-SRNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FggsDing\u002FBi-SRNet?style=social)|\n| 2022 | [SemiCD](https:\u002F\u002Fgithub.com\u002Fwgcban\u002FSemiCD) | 重访半监督遥感影像变化检测中的一致性正则化 | [arXiv2022](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.08454) | 半监督、一致性正则化 | WHU-CD、LEVIR-CD | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fwgcban\u002FSemiCD.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fwgcban\u002FSemiCD?style=social)|\n| 2022 | [FCCDN](https:\u002F\u002Fgithub.com\u002Fchenpan0615\u002FFCCDN_pytorch) | FCCDN：用于VHR影像变化检测的特征约束网络 | [ISPRS P&RS 2022](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271622000636) | 自监督学习、非局部特征金字塔网络、双编码器-解码器骨干|WHU-CD、LEVIR-CD、SECOND| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fchenpan0615\u002FFCCDN_pytorch.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fchenpan0615\u002FFCCDN_pytorch?style=social)|\n| 2021 | [ChangeStar](https:\u002F\u002Fgithub.com\u002FZ-Zheng\u002FChangeStar) | 变化无处不在：遥感影像中的单时相监督目标变化检测 | [ICCV2021](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FICCV2021\u002Fpapers\u002FZheng_Change_Is_Everywhere_Single-Temporal_Supervised_Object_Change_Detection_in_Remote_ICCV_2021_paper.pdf) | 单时相监督、时间对称性| xBD、SpaceNet2、WHU-CD、LEVIR-CD| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZ-Zheng\u002FChangeStar.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-Zheng\u002FChangeStar?style=social)|\n| 2021 | [ChangeOS](https:\u002F\u002Fgithub.com\u002FZ-Zheng\u002FChangeOS) | 基于深度对象导向语义变化检测框架的快速灾害响应建筑损毁评估：从自然灾害到人为灾害 | [RSE2021](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425721003564) | 语义变化检测、灾害响应、OBIA| xBD、2020年贝鲁特港口爆炸、2021年巴塔军营爆炸 | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FZ-Zheng\u002FChangeOS.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FZ-Zheng\u002FChangeOS?style=social)|\n| 2021 | [Optical-SAR-CD](https:\u002F\u002Fgitlab.lrz.de\u002Fai4eo\u002Fcd\u002F-\u002Ftree\u002Fmain\u002FsarOpticalMultisensorTgrs2021) | 自监督多传感器变化检测 | [TGRS2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9538396) | 自监督、多传感器 | OSCD（哨兵-2和哨兵-1） | - |\n| 2021 | [CEECNet](https:\u002F\u002Fgithub.com\u002Ffeevos\u002Fceecnet) | 寻找变化？掷骰子并吸引注意力 | [RS2021](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F13\u002F18\u002F3707) | 骰子相似度、注意力模块 | WHU-CD、LEVIR-CD | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Ffeevos\u002Fceecnet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ffeevos\u002Fceecnet?style=social)|\n| 2021 | [ESCNet](https:\u002F\u002Fgithub.com\u002FBobholamovic\u002FESCNet) | ESCNet：一个端到端的超像素增强型变化检测网络，适用于超高分辨率遥感影像 | [TNNLS2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9474911) | 超像素分割、超像素自适应合并 | SZTAKI、CDD| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FBobholamovic\u002FESCNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FBobholamovic\u002FESCNet?style=social)|\n| 2021 | [SeCo](https:\u002F\u002Fgithub.com\u002FElementAI\u002Fseasonal-contrast) | 季节对比：来自未加工遥感数据的无监督预训练 | [ICCV2021](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FICCV2021\u002Fhtml\u002FManas_Seasonal_Contrast_Unsupervised_Pre-Training_From_Uncurated_Remote_Sensing_Data_ICCV_2021_paper.html) | 自监督学习| BigEarthNet、EuroSAT、OSCD | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002FElementAI\u002Fseasonal-contrast.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FElementAI\u002Fseasonal-contrast?style=social)|\n| 2021 | [SRCDNet](https:\u002F\u002Fgithub.com\u002Fliumency\u002FSRCDNet) | 基于超分辨率的带堆叠注意力模块的变化检测网络，适用于不同分辨率的影像 | [TGRS2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9472869) | 超分辨率、度量学习 | BCDD、CDD、GZ-CD | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fliumency\u002FSRCDNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fliumency\u002FSRCDNet?style=social)|\n| 2021 | [IAug-CDNet](https:\u002F\u002Fgithub.com\u002Fjustchenhao\u002FIAug_CDNet) | 针对遥感影像中建筑物变化检测的对抗性实例增强 | [TGRS2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9386248) | 对抗性实例增强、合成数据| WHU-CD、LEVIR-CD | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fjustchenhao\u002FIAug_CDNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjustchenhao\u002FIAug_CDNet?style=social)|\n| 2021 | [SNUNet-CD](https:\u002F\u002Fgithub.com\u002Flikyoo\u002Fopen-cd\u002F) | SNUNet-CD：一种用于VHR影像变化检测的密集连接暹罗网络 | [GRSL2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9355573) | 全卷积暹罗网络 | CDD | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Flikyoo\u002Fopen-cd.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flikyoo\u002Fopen-cd?style=social)|\n| 2021 | [DDNet](https:\u002F\u002Fgithub.com\u002Fsummitgao\u002FSAR_CD_DDNet) | 使用双域网络进行合成孔径雷达影像的变化检测 | [GRSL2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9420150) | SAR、频域 | 渥太华数据集、苏尔茨伯格数据集、黄河数据集| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fsummitgao\u002FSAR_CD_DDNet.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsummitgao\u002FSAR_CD_DDNet?style=social)|\n| 2021 | [ACDA](https:\u002F\u002Fgithub.com\u002Fmeiqihu\u002FACDA) | 基于自编码器的高光谱异常变化检测 | [JSTARS2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9380336) | 高光谱、异常变化检测、自编码器 | 维亚雷焦2013年事件| ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fmeiqihu\u002FACDA.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fmeiqihu\u002FACDA?style=social)|\n| 2018 | [FC-EF、FC-Siam-diff、FC-Siam-conc](https:\u002F\u002Fgithub.com\u002Frcdaudt\u002Ffully_convolutional_change_detection) | 用于变化检测的全卷积暹罗网络 | [ICIP2018](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8451652) | 全卷积暹罗网络 | SZTAKI、OSCD | ![最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Frcdaudt\u002Ffully_convolutional_change_detection.svg?style=flat&logo=github&label=Last%20Commit)![GitHub星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Frcdaudt\u002Ffully_convolutional_change_detection?style=social) |\n\n## 传统方法\n\n| 年份 | 缩写 | 标题 | 出版物 | 关键词 | 实验数据集 |\n| :--- | :--- | :--- | :--- | :--- | :--- |\n|2025|[PWTT](https:\u002F\u002Fgithub.com\u002Foballinger\u002FPWTT)|基于哨兵-1号影像的像素级T检验的开放获取战损检测|[RSE2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425725004298?dgcid=rss_sd_all)|概率性变化检测；建筑物损毁评估；武装冲突|[UNOSAT损毁标注数据集](https:\u002F\u002Fgithub.com\u002Foballinger\u002FPWTT)|\n|2021|[SiROC](https:\u002F\u002Fgithub.com\u002Flukaskondmann\u002FSiROC)|面向光学卫星影像无监督变化检测的空间上下文感知|[TGRS2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9627707)|多时相、光学影像、无监督、城市分析|OSCD、贝鲁特港口爆炸数据集、农业数据集、阿尔卑斯山数据集|\n|2015|[CCDC](https:\u002F\u002Fgithub.com\u002FGERSL\u002FCCDC)|基于所有可用的Landsat数据生成合成Landsat影像：预测任意时刻的Landsat地表反射率|[RSE2015](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425715000590)|合成、Landsat、地表反射率、时间序列模型|美国本土不同地点的六景Landsat影像|\n|2013|SFA|用于多光谱影像变化检测的慢特征分析|[TGRS2013](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F6553145)|图像变换、慢特征分析|台州ETM数据集、昆山ETM数据|\n|2010|CVAPS|后验概率空间中的变化矢量分析：一种新的土地覆盖变化检测方法|[GRSL2010](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F5597922)|CVA、土地覆盖变化、分类后比较（PCC）、后验概率空间|中国北京顺义区的多时相Landsat专题制图仪（TM）数据|\n|2009|PCA-Kmeans|利用主成分分析和k均值聚类进行卫星影像无监督变化检测|[GRSL2009](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F5196726)|k均值聚类、多时相卫星影像、光学影像、主成分分析（PCA）|内华达州里诺市太浩湖的光学影像|\n|2007|[IR-MAD](http:\u002F\u002Fpeople.compute.dtu.dk\u002Falan\u002Fsoftware.html) | 正则化迭代加权多元变化检测 | [TIP2007](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F4060945) | 典型相关分析（CCA）、迭代加权多元变化检测（IR-MAD）、MAD变换、正则化或惩罚|部分构建的瑞典北部Landsat TM数据；肯尼亚基安布县的SPOT HRV数据；德国瓦金-塔欣格湖的Hymap数据|\n|2003|ICVA|利用改进的变化矢量分析进行土地利用\u002F土地覆盖变化检测|[PERS2003](https:\u002F\u002Fwww.ingentaconnect.com\u002Fcontent\u002Fasprs\u002Fpers\u002F2003\u002F00000069\u002F00000004\u002Fart00004)|改进的CVA、双窗口灵活步长搜索（DFPS）、最小距离分类技术|中国北京海淀区的多时相Landsat TM影像|\n|1998|[MAD](http:\u002F\u002Fpeople.compute.dtu.dk\u002Falan\u002Fsoftware.html)|在多光谱、双时相影像数据中进行多元变化检测（MAD）及MAF后处理：变化检测研究的新方法|[RSE1998](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425797001624)|多元变化检测（MAD）、最大自相关因子（MAF）、典型相关分析（CCA）|澳大利亚昆士兰州的两景Landsat MSS影像；加州海流系统厄尔尼诺阶段的两景AVHRR影像|\n|1980|CVA|变化矢量分析：一种利用Landsat检测森林变化的方法|[LARS研讨会1980年](https:\u002F\u002Fdocs.lib.purdue.edu\u002Fcgi\u002Fviewcontent.cgi?article=1386&context=lars_symp)|变化矢量分析、森林变化检测、Landsat多光谱数据、空间光谱聚类、帽状变换|覆盖爱达荷州克利尔沃特国家森林帕卢斯地区的三个木材采伐区的Landsat数据|\n\n\n# 综述论文\n\n| 年份 | 标题 | 发表刊物 | 描述 |\n| :--- | :--- | :--- | :--- | \n|2025|遥感智能变化检测的深度学习方法：演变与发展趋势|[测绘学报2025](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002FjZp_79g-L_LTCJpNRDOMdQ)|本文系统综述了深度学习在遥感变化检测中的研究进展，围绕变化特征表达和网络学习策略两大核心问题，梳理了从局部到时空联合、单一到多模态、轻量到大模型、二值到多类别特征表达的发展趋势，以及从全监督向弱\u002F半监督和无监督学习的演进路径，并指出图文融合、生成式模型和人机协同是未来提升智能化水平的关键方向。|\n|2025|深度学习遥感变化检测研究进展：像素-对象-场景|[遥感技术与应用2025](http:\u002F\u002Fwww.rsta.ac.cn\u002FCN\u002F10.11873\u002Fj.issn.1004-0323.2025.4.0783)|本文从像素级、对象级和场景级三个层次系统总结深度学习在遥感变化检测中的研究进展，结合典型案例分析其实际应用，并展望其未来发展趋势。|\n| 2025 | 图论在卫星影像时间序列中的应用 | [arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.16685) | 探讨了基于图论的技术在卫星影像时间序列的时空分析中的集成应用，重点介绍了时空图的构建及其在土地覆盖制图、水资源预测等任务中的应用，并展望了未来的研究方向。 |\n| 2025 | 遥感变化检测中样本高效深度学习方法综述：任务、策略与挑战 | [GRSM2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F10884556) | 总结了在样本有限情况下，针对不同任务和策略的深度学习变化检测方法的相关文献，讨论了近年来为解决数据稀缺问题而在图像生成、自监督学习和视觉基础模型方面取得的进展。 |\n| 2025 | 光学遥感影像的变化检测深度学习技术：现状、展望与挑战 | [JAG2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1569843224006381) | 系统地总结了光学遥感影像变化检测的数据集、理论和方法，从算法粒度的角度分析了基于人工智能的算法，并讨论了人工智能时代下的挑战与趋势。相关更新可在[daifeng2016\u002FAwesome-Optical-Remote-Sensing-Datasets-and-Methods](https:\u002F\u002Fgithub.com\u002Fdaifeng2016\u002FAwesome-Optical-Remote-Sensing-Datasets-and-Methods)中找到。 |\n| 2024 | 基于多模态遥感影像融合的深度学习变化检测综述 | [RS2024](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F16\u002F20\u002F3852) | 探讨了利用多源异质数据（包括多光谱、高光谱、雷达及多时相影像）进行遥感影像变化检测的深度学习方法，并讨论了公开数据集、模型、面临的挑战以及未来的发展趋势。 |\n| 2024 | 卫星影像时间序列分析中的深度学习：综述 | [GRSM2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F10529247) | 总结了利用深度学习对卫星影像时间序列（SITS）数据进行建模以分析环境和农业变量的最新方法，着重探讨了SITS数据的复杂性及其在土地和自然资源管理中的应用。 |\n| 2024 | 基于深度学习的遥感影像变化检测进展与挑战：多种学习范式视角下的综述 | [RS2024](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F16\u002F5\u002F804) | 全面审视了基于深度学习的遥感变化检测技术，涵盖了关键架构、学习范式（监督、半监督、弱监督和无监督）、基准数据集，以及自监督学习、基础模型和多模态数据融合等新兴机遇；同时指出了当前的挑战和推动该领域发展的潜在研究方向。 |\n| 2024 | 近十年来遥感变化检测方法综述 | [RS2024](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F16\u002F13\u002F2355) | 对过去十年中基于深度学习的遥感变化检测进行了全面调查，从算法粒度、监督模式和框架等多个角度提供了系统的分类体系，并回顾了关键数据集、评估指标、最新性能表现，同时识别出具有前景的未来研究方向，以指导和激励相关领域的研究者。 |\n| 2023 | 深度学习遥感变化检测综述：文献计量与分析 | [遥感学报2023](https:\u002F\u002Fwww.ygxb.ac.cn\u002Fzh\u002Farticle\u002Fdoi\u002F10.11834\u002Fjrs.20222156\u002F) | 本文综述了基于深度学习的遥感变化检测研究进展，从像素、对象和场景三个粒度系统梳理方法体系，指出对象与场景级方法更具优势，并强调未来需突破多模态异质数据融合、非理想样本处理及多元变化信息提取等挑战，以推动其在多领域更广泛、智能化的应用。 |\n| 2023 | 人工智能时代的遥感变化检测技术：继承、发展与挑战 | [遥感学报2023](https:\u002F\u002Fwww.ygxb.ac.cn\u002Fzh\u002Farticle\u002Fdoi\u002F10.11834\u002Fjrs.20222199\u002F) | 本文系统梳理了人工智能时代下光学遥感影像变化检测技术从传统方法向数据—模型—知识联合驱动的智能化转型历程，分析了无监督、监督与弱监督三类方法的发展趋势，并指出未来需重点突破模型可解释性、泛化迁移能力及跨场景跨领域应用等关键瓶颈问题。相关讲解视频详见：[【前沿进展】变化检测与深度学习](https:\u002F\u002Fwww.bilibili.com\u002Fvideo\u002FBV1Cf4y1Y77x\u002F?vd_source=22b45bd19426f7fd4ee5b0e1055bfc8c)。 |\n| 2023 | 基于航空与地面点云的三维城市对象变化检测综述 | [JAG2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1569843223000808) | 回顾了利用点云数据进行城市对象三维变化检测的最新进展，分析了建筑物、街景、城市树木和建筑工地等情况，并讨论了数据来源、方法及未来面临的挑战。 |\n| 2023 | 基于点云的城市对象变化检测综述 | [ISPRS P&RS 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271623000163) | 提供了一份关于使用点云数据进行城市对象三维变化检测的全面综述，内容涵盖数据配准、方差估计、变化分析，以及在土地覆盖监测、植被调查和施工自动化中的应用。 |\n|2022|基于异构遥感影像的土地覆盖变化检测：综述、进展与展望|[IEEE PROC 2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9955391)|全面概述了异构遥感影像变化检测（Hete-CD），总结了其文献、主要技术、数据集、性能评估、面临的挑战及未来发展方向，旨在为研究人员和从业者提供一站式参考。|\n|2022|遥感变化检测中的深度学习：综述|[GSIS2022](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F10095020.2022.2085633)|通过分析深度学习在信息表征、方法进步和跨光谱、空间、时间及多传感器维度上的性能提升，探讨了深度学习为何能增强遥感变化检测能力；同时指出了深度学习变化检测发展的关键局限性和未来方向。|\n| 2022 | 土地覆盖变化检测技术：极高分辨率光学影像 | [GRSM2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9477629) | 回顾了利用极高分辨率遥感影像进行土地覆盖变化检测的技术，重点探讨了捕捉细节变化的能力，并讨论了各种方法和应用场景。 |\n| 2022 | 基于深度学习的高分辨率遥感影像变化检测综述 | [RS2022](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F14\u002F7\u002F1552) | 回顾了基于深度学习的高分辨率遥感影像变化检测方法，按网络架构对算法进行了分类，并讨论了数据集、评估指标、面临的挑战以及未来的研究方向。 |\n|2022|卫星遥感影像的多类别变化检测综述|[GSIS2022](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F10095020.2022.2128902)|全面回顾了遥感领域的多类别变化检测（MCD），内容包括其背景、关键挑战、基准数据集、方法分类、实际应用及未来研究方向，旨在填补现有文献的空白，为推进超越传统二元检测的精细化土地变化分析提供基础性参考。|\n|2021|极高空间分辨率光学遥感影像的变化检测：方法、应用及未来方向|[GRSM2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9395350)|全面概述了极高空间分辨率（≤5 m）遥感影像中的变化检测，系统地考察了当前方法、实际应用和未来研究方向，以应对光谱信息有限、光谱变异性和几何畸变等挑战。|\n| 2020 | 多源多目标场景下基于遥感影像的变化检测方法综述 | [RS2020](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F12\u002F15\u002F2460) | 调查了多源遥感影像和多目标场景下的变化检测方法，总结了一个包含变化信息提取、数据融合和分析的一般框架，并讨论了未来的发展方向。 |\n| 2020 | 基于人工智能的变化检测：最新进展与挑战 | [RS2020](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F12\u002F10\u002F1688) | 回顾了人工智能在变化检测中的最新方法、应用和挑战，内容涵盖数据来源、深度学习框架和无监督方案，并讨论了异构数据处理和人工智能可靠性等问题。相关更新可在[MinZHANG-WHU\u002FChange-Detection-Review](https:\u002F\u002Fgithub.com\u002FMinZHANG-WHU\u002FChange-Detection-Review)中查看。|\n| 2019 | 多时相高光谱影像变化检测综述：当前技术、应用与挑战 | [GRSM2019](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8738052) | 提供了一篇关于高光谱遥感影像变化检测的全面综述，内容包括基本概念、方法分类、当前技术以及关键挑战；同时通过实验结果展示了最先进的方法，以突出利用高光谱分辨率进行精细化土地覆盖变化监测的独特潜力和复杂性。 |\n|2018|多时相遥感影像变化检测方法综述|[武汉大学学报 (信息科学版) 2018](http:\u002F\u002Fch.whu.edu.cn\u002Farticle\u002Fid\u002F6272)|本文系统回顾了多时相遥感影像变化检测技术的发展历程，从预处理、方法分类到精度评价全面梳理研究进展，指出当前尚无普适性通用方法，并分析核心难点与应对策略，旨在推动该领域向更深入、更系统方向发展。|\n|2017|多时相遥感影像变化检测的现状与展望|[测绘学报2017](https:\u002F\u002Fhtml.rhhz.net\u002FCHXB\u002Fhtml\u002F2017-10-1447.htm)|本文围绕多时相遥感影像变化检测的基本流程，从预处理、方法、阈值分割到精度评价系统梳理最新研究进展，总结其在生态环境监测与城市发展等领域的应用，并展望高光谱与高分辨率影像驱动下的未来发展方向。|\n| 2017 | 利用Landsat时间序列进行变化检测：频率、预处理、算法和应用综述 | [ISPRS P&RS 2017](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS092427161730103X) | 回顾了基于Landsat时间序列的变化检测研究，内容包括频率、预处理步骤、算法和应用，并讨论了Landsat数据免费开放对变化检测方法的影响。 |\n| 2016 | 用于土地覆盖分类的光学遥感时间序列数据：综述 | [ISPRS P&RS 2016](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271616000769) | 回顾了利用光学遥感时间序列数据进行土地覆盖分类的情况，讨论了生成年度土地覆盖产品以及整合时间序列信息的方法所面临的问题和机遇。 |\n|2016|SAR影像变化检测研究进展|[计算机研究与发展2015](https:\u002F\u002Fcrad.ict.ac.cn\u002Fcn\u002Farticle\u002FY2016\u002FI1\u002F123)|本文系统梳理了SAR影像变化检测的经典流程与传统方法，重点综述近年来在差异图生成及阈值、聚类、图切、水平集等分析方法上的新兴算法改进，并通过两组数据集定量验证其性能，最后展望了该领域仍需深入研究的关键方向。|\n| 2015 | 遥感光学影像变化检测技术的批判性综合 | [RSE2015](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425715000152) | 提供了一篇关于遥感变化检测技术的批判性综合文章，按照分析单元和比较方法对文献进行整理，以减少概念重叠并指导未来研究。 |\n| 2013 | 基于遥感影像的变化检测：从像素级到对象级方法 | [ISPRS P&RS 2013](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271613000804) | 回顾了从像素级到对象级的变化检测方法，讨论了随着超高分辨率影像出现，对象级方法和数据挖掘技术的潜力。 |\n| 2012 | 基于对象的变化检测 | [IJRS2012](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Fabs\u002F10.1080\u002F01431161.2011.648285) | 讨论了利用高空间分辨率影像进行的基于对象的变化检测（OBCD），将其与像素级方法进行比较，并回顾了用于提取详细变化信息的算法和应用。 |\n| 2012 | 基于Landsat数据的大面积土地覆盖变化监测综述 | [RSE2012](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425712000314) | 回顾了利用Landsat数据进行大面积土地覆盖变化监测的方法，重点讨论了森林覆盖变化，并探讨了辐射校正、时间更新以及地形校正数据免费开放带来的影响。 |\n|2011|多时相遥感影像变化检测综述|[地理信息世界2011](https:\u002F\u002Fd.wanfangdata.com.cn\u002Fperiodical\u002FCh9QZXJpb2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2Rp......| 年份 | 标题 | 发表刊物 | 描述 |\n| :--- | :--- | :--- | :--- | \n|2025|遥感智能变化检测的深度学习方法：演变与发展趋势|[测绘学报2025](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002FjZp_79g-L_LTCJpNRDOMdQ)|本文系统综述了深度学习在遥感变化检测中的研究进展，围绕变化特征表达和网络学习策略两大核心问题，梳理了从局部到时空联合、单一到多模态、轻量到大模型、二值到多类别特征表达的发展趋势，以及从全监督向弱\u002F半监督和无监督学习的演进路径，并指出图文融合、生成式模型和人机协同是未来提升智能化水平的关键方向。|\n|2025|深度学习遥感变化检测研究进展：像素-对象-场景|[遥感技术与应用2025](http:\u002F\u002Fwww.rsta.ac.cn\u002FCN\u002F10.11873\u002Fj.issn.1004-0323.2025.4.0783)|本文从像素级、对象级和场景级三个层次系统总结深度学习在遥感变化检测中的研究进展，结合典型案例分析其实际应用，并展望其未来发展趋势。|\n| 2025 | 关于图在网络卫星影像时间序列中的应用 | [arXiv2025](https:\u002F\u002Farxiv.org\u002Fabs\u002F2505.16685) | 探讨了将基于图的技术整合用于卫星影像时间序列的时空分析，重点介绍了时空图的构建及其在土地覆盖制图、水资源预测等任务中的应用，并展望了未来的研究方向。 |\n| 2025 | 遥感变化检测中样本高效深度学习方法综述：任务、策略与挑战 | [GRSM2025](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F10884556) | 总结了在样本有限情况下，针对不同任务和策略的深度学习变化检测方法的相关文献，讨论了近年来为解决数据稀缺问题而在图像生成、自监督学习和视觉基础模型方面的最新进展。 |\n| 2025 | 光学遥感影像的变化检测深度学习技术：现状、展望与挑战 | [JAG2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1569843224006381) | 系统地总结了光学遥感影像变化检测的数据集、理论和方法，从算法粒度的角度分析了基于人工智能的算法，并探讨了人工智能时代下的挑战与趋势。相关更新可在[daifeng2016\u002FAwesome-Optical-Remote-Sensing-Datasets-and-Methods](https:\u002F\u002Fgithub.com\u002Fdaifeng2016\u002FAwesome-Optical-Remote-Sensing-Datasets-and-Methods)中找到。 |\n| 2024 | 基于多模态遥感影像融合的深度学习变化检测综述 | [RS2024](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F16\u002F20\u002F3852) | 探讨了利用多源异质数据（如多光谱、高光谱、雷达及多时相影像）进行遥感影像变化检测的深度学习方法，并讨论了公开数据集、现有模型、面临的挑战及未来趋势。 |\n| 2024 | 卫星影像时间序列分析中的深度学习：综述 | [GRSM2024](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F10529247) | 总结了利用深度学习对卫星影像时间序列（SITS）数据进行建模以监测环境和农业变量的最新方法，着重解决了SITS数据的复杂性及其在土地和自然资源管理中的应用问题。 |\n| 2024 | 基于深度学习的遥感影像变化检测进展与挑战：多种学习范式视角下的综述 | [RS2024](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F16\u002F5\u002F804) | 全面审视了基于深度学习的遥感变化检测技术，涵盖了关键架构、学习范式（监督、半监督、弱监督和无监督）、基准数据集，以及自监督学习、基础模型和多模态数据融合等新兴机遇；同时指出了当前的挑战及推动该领域发展的潜在研究方向。 |\n| 2024 | 近十年来遥感影像变化检测方法综述 | [RS2024](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F16\u002F13\u002F2355) | 对过去十年中基于深度学习的遥感变化检测进行了全面调查，从算法粒度、监督模式和框架等多个角度构建了系统的分类体系，并回顾了关键数据集、评估指标、最新性能表现，同时识别出具有前景的未来研究方向，以指导和激励相关领域的研究者。 |\n| 2023 | 深度学习的遥感变化检测综述：文献计量与分析 | [遥感学报2023](https:\u002F\u002Fwww.ygxb.ac.cn\u002Fzh\u002Farticle\u002Fdoi\u002F10.11834\u002Fjrs.20222156\u002F) | 本文综述了基于深度学习的遥感变化检测研究进展，从像素、对象和场景三个粒度系统梳理方法体系，指出对象与场景级方法更具优势，并强调未来需突破多模态异质数据融合、非理想样本处理及多元变化信息提取等挑战，以推动其在多领域更广泛、智能化的应用。 |\n| 2023 | 人工智能时代的遥感变化检测技术：继承、发展与挑战 | [遥感学报2023](https:\u002F\u002Fwww.ygxb.ac.cn\u002Fzh\u002Farticle\u002Fdoi\u002F10.11834\u002Fjrs.20222199\u002F) | 本文系统梳理了人工智能时代下光学遥感影像变化检测技术从传统方法向数据—模型—知识联合驱动的智能化转型历程，分析了无监督、监督与弱监督三类方法的发展趋势，并指出未来需重点突破模型可解释性、泛化迁移能力及跨场景跨领域应用等关键瓶颈问题。相关讲解视频详见：[【前沿进展】变化检测与深度学习](https:\u002F\u002Fwww.bilibili.com\u002Fvideo\u002FBV1Cf4y1Y77x\u002F?vd_source=22b45bd19426f7fd4ee5b0e1055bfc8c)。 |\n| 2023 | 基于航空与地面点云的三维城市物体变化检测综述 | [JAG2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1569843223000808) | 回顾了利用点云数据进行城市物体三维变化检测的最新进展，分析了建筑物、街道景观、城市树木和建筑工地等情况，并讨论了数据来源、方法及未来挑战。 |\n| 2023 | 基于点云的城市物体变化检测综述 | [ISPRS P&RS 2023](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271623000163) | 提供了一份关于使用点云数据进行城市物体三维变化检测的全面综述，内容涵盖数据配准、方差估计、变化分析，以及在土地覆盖监测、植被调查和施工自动化中的应用。 |\n|2022|基于异质遥感影像的土地覆盖变化检测：综述、进展与展望|[IEEE PROC 2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9955391)|全面概述了异质遥感影像变化检测（Hete-CD），总结了其文献、主要技术、数据集、性能评估、面临的挑战及未来发展方向，旨在为研究人员和从业者提供一站式参考。|\n|2022|遥感影像变化检测中的深度学习：综述|[GSIS2022](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F10095020.2022.2085633)|通过分析深度学习在信息表征、方法论进步以及光谱、空间、时间与多传感器维度上的性能提升，探讨了为何深度学习能够增强遥感变化检测能力；同时指出了深度学习变化检测发展的关键局限性和未来方向。|\n| 2022 | 土地覆盖变化检测技术：极高分辨率光学影像 | [GRSM2022](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9477629) | 回顾了使用极高分辨率遥感影像进行土地覆盖变化检测的技术，重点探讨了捕捉细节变化的能力，并讨论了各种方法和应用。 |\n| 2022 | 基于深度学习的高分辨率遥感影像变化检测综述 | [RS2022](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F14\u002F7\u002F1552) | 回顾了基于深度学习的高分辨率遥感影像变化检测方法，按网络架构对算法进行了分类，并讨论了数据集、评估指标、面临的挑战以及未来的研究方向。 |\n|2022|卫星遥感影像多类别变化检测综述|[GSIS2022](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F10095020.2022.2128902)|全面回顾了遥感领域的多类别变化检测（MCD），内容包括其背景、关键挑战、基准数据集、方法分类、实际应用及未来研究方向，旨在填补现有文献的空白，为推进精细土地变化分析、超越传统二元检测提供基础性参考。|\n|2021|极高空间分辨率光学遥感影像的变化检测：方法、应用与未来方向|[GRSM2021](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9395350)|全面概述了极高空间分辨率（≤5 m）遥感影像中的变化检测，系统地考察了当前方法、实际应用以及未来研究方向，以应对光谱信息有限、光谱变异性和几何畸变等挑战。|\n| 2020 | 多源多目标场景下基于遥感影像的变化检测方法综述 | [RS2020](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F12\u002F15\u002F2460) | 调查了多源遥感影像和多目标场景下的变化检测方法，总结了一个包含变化信息提取、数据融合和分析的一般框架，并讨论了未来方向。 |\n| 2020 | 基于人工智能的变化检测：最新进展与挑战 | [RS2020](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F12\u002F10\u002F1688) | 回顾了人工智能在变化检测中的最新方法、应用和挑战，内容涵盖数据来源、深度学习框架和无监督方案，并讨论了异质数据处理和AI可靠性等问题。相关更新可在[MinZHANG-WHU\u002FChange-Detection-Review](https:\u002F\u002Fgithub.com\u002FMinZHANG-WHU\u002FChange-Detection-Review)中查看。|\n| 2019 | 多时相高光谱影像变化检测综述：当前技术、应用与挑战 | [GRSM2019](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8738052) | 提供了一篇关于高光谱遥感影像变化检测的全面综述，内容包括基本概念、方法分类、当前技术及关键挑战，并通过实验结果展示了最先进的方法，以突出利用高光谱分辨率进行精细土地覆盖变化监测的独特潜力和复杂性。 |\n|2018|多时相遥感影像变化检测方法综述|[武汉大学学报 (信息科学版) 2018](http:\u002F\u002Fch.whu.edu.cn\u002Farticle\u002Fid\u002F6272)|本文系统回顾了多时相遥感影像变化检测技术的发展历程，从预处理、方法分类到精度评价全面梳理研究进展，指出当前尚无普适性通用方法，并分析核心难点与应对策略，旨在推动该领域向更深入、更系统方向发展。|\n|2017|多时相遥感影像变化检测的现状与展望|[测绘学报2017](https:\u002F\u002Fhtml.rhhz.net\u002FCHXB\u002Fhtml\u002F2017-10-1447.htm)|本文围绕多时相遥感影像变化检测的基本流程，从预处理、方法、阈值分割到精度评价系统梳理最新研究进展，总结其在生态环境监测与城市发展等领域的应用，并展望高光谱与高分辨率影像驱动下的未来发展方向。|\n| 2017 | 利用Landsat时间序列进行变化检测：频率、预处理、算法和应用综述 | [ISPRS P&RS 2017](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS092427161730103X) | 回顾了基于Landsat时间序列的变化检测研究，内容包括频率、预处理步骤、算法和应用，并讨论了Landsat数据免费开放对变化检测方法的影响。 |\n| 2016 | 用于土地覆盖分类的光学遥感时间序列数据：综述 | [ISPRS P&RS 2016](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271616000769) | 回顾了利用光学遥感时间序列数据进行土地覆盖分类的情况，讨论了生成年度土地覆盖产品以及整合时间序列信息的方法所面临的问题和机遇。 |\n|2016|SAR影像变化检测研究进展|[计算机研究与发展2015](https:\u002F\u002Fcrad.ict.ac.cn\u002Fcn\u002Farticle\u002FY2016\u002FI1\u002F123)|本文系统梳理了SAR影像变化检测的经典流程与传统方法，重点综述近年来在差异图生成及阈值、聚类、图切、水平集等分析方法上的新兴算法改进，并通过两组数据集定量验证其性能，最后展望了该领域仍需深入研究的关键方向。|\n| 2015 | 遥感光学影像变化检测技术的批判性综合 | [RSE2015](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425715000152) | 提供了一篇关于遥感变化检测技术的批判性综合文章，按照分析单元和比较方法对文献进行整理，以减少概念重叠并指导未来研究。 |\n| 2013 | 基于遥感影像的变化检测：从像素级到对象级方法 | [ISPRS P&RS 2013](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0924271613000804) | 回顾了从像素级到对象级的变化检测方法，讨论了随着超高分辨率影像出现，对象级方法和数据挖掘技术的潜力。 |\n| 2012 | 基于对象的变化检测 | [IJRS2012](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Fabs\u002F10.1080\u002F01431161.2011.648285) | 讨论了利用高空间分辨率影像进行的基于对象的变化检测（OBCD），将其与像素级方法进行对比，并回顾了用于提取详细变化信息的算法和应用。 |\n| 2012 | 基于Landsat数据的大面积土地覆盖变化监测综述 | [RSE2012](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0034425712000314) | 回顾了利用Landsat数据进行大面积土地覆盖变化监测的方法，重点讨论了森林覆盖变化，并探讨了辐射校正、时间更新以及地形校正数据免费开放的影响。 |\n|2011|多时相遥感影像变化检测综述|[地理信息世界2011](https:\u002F\u002Fd.wanfangdata.com.cn\u002Fperiodical\u002FCh9QZXJpb2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2RpY2......\n\n# 竞赛\n\n| 年份 | 目标 | 比赛名称 | 赛道 | 图像对数 | 图像尺寸 | 分辨率 | 备注 |\n| --- | --- | --- | --- | --- | --- | --- | --- |\n|2025|建筑物|[AI用于地震响应](https:\u002F\u002Fplatform.ai4eo.eu\u002Fai-for-earthquake-response)|通过分析高分辨率的灾前和灾后卫星影像，检测受损与未受损的建筑物|-|-|-|-|\n| 2024 | 土地覆盖| [ISPRS第一技术委员会多模态遥感应用算法智能解译大赛](https:\u002F\u002Fwww.gaofen-challenge.com\u002Fchallenge) |基于高分辨率可见光图像的感兴趣区域内部变化智能检测| 4,000 | 512×512 | 2m |-|\n| 2024 | 土地覆盖 | [“吉林一号”杯卫星遥感应用青年创新创业大赛](https:\u002F\u002Fwww.jl1mall.com\u002Fcontest\u002FmatchMenu) |高分辨率遥感影像全要素变化检测研究| 5,000 | 512×512 |\u003C0.75m|-|\n| 2023 | 农田 | [“吉林一号”杯卫星遥感应用青年创新创业大赛](https:\u002F\u002Fwww.jl1mall.com\u002Fcontest\u002Fmatch\u002Finfo?id=1645664411716952066) |基于高分辨率卫星影像的耕地变化检测| 8,000 | 256×256 |\u003C0.75m|-|\n| 2023 | 土地覆盖 | [“国丰东方慧眼杯”遥感影像智能处理算法大赛](http:\u002F\u002Frsipac.whu.edu.cn\u002F) |对象级变化检测| >6,000 | 512×512 | 1-2m |-|\n| 2022 | 土地覆盖 | [“航天宏图杯”遥感影像智能处理算法大赛](http:\u002F\u002Frsipac.whu.edu.cn\u002F) |遥感影像变化检测| >6,000 | 512×512 | 1-2m |-|\n| 2022 | 洪水 | [SpaceNet8: Flood Detection Challenge](https:\u002F\u002Fjoin.topcoder.com\u002Fspacenet) |使用多分类分割进行洪水检测挑战| 12 | 1,300×1,300 | 0.3-0.8m |[数据集论文](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2022W\u002FEarthVision\u002Fpapers\u002FHansch_SpaceNet_8_-_The_Detection_of_Flooded_Roads_and_Buildings_CVPRW_2022_paper.pdf), [解决方案论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F10281500)|\n| 2021 |土地覆盖|[IEEE GRSS数据融合竞赛](https:\u002F\u002Fwww.grss-ieee.org\u002Fcommunity\u002Ftechnical-committees\u002F2021-ieee-grss-data-fusion-contest-track-msd\u002F)|多时相语义变化检测|2,250|-|-|[成果论文](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F9690575)|\n| 2021 |土地覆盖|[DynamicEarthNet挑战赛](https:\u002F\u002Fcodalab.lisn.upsaclay.fr\u002Fcompetitions\u002F2882) |弱监督无监督二值土地覆盖变化检测、多类别变化检测|54,750|1,024x1,024|3.0|[第一名解决方案](https:\u002F\u002Fgithub.com\u002Fsolcummings\u002Fearthvision2021-weakly-supervised), [数据集论文](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2022\u002Fpapers\u002FToker_DynamicEarthNet_Daily_Multi-Spectral_Satellite_Dataset_for_Semantic_Change_Segmentation_CVPR_2022_paper.pdf)|\n| 2021 | 土地覆盖 | [“昇腾杯”遥感影像智能处理算法大赛](http:\u002F\u002Frsipac.whu.edu.cn\u002Fsubject_two_2021) | 耕地建筑物变化检测 | >6,000 | 512×512 | 1-2m |[前四名解决方案](https:\u002F\u002Fgithub.com\u002FWangZhenqing-RS\u002F2021rsipac_changeDetection_TOP4), [前五名解决方案](https:\u002F\u002Fgithub.com\u002F78666621\u002F2021rsipac_changeDetection_TOP5)|\n| 2021 | 建筑物 | [遥感图像智能解译技术挑战赛](https:\u002F\u002Fcaptain-whu.github.io\u002FPRCV2021_RS\u002Ftasks.html) | 遥感图像建筑物变化检测 | 10,000 | 512×512 | - |-|[第二名解决方案](https:\u002F\u002Fgithub.com\u002Fbusiniaoo\u002FPRCV2021-Change-Detection-Contest-2nd-place-Solution), [第三名解决方案](https:\u002F\u002Fgithub.com\u002Flikyoo\u002FPRCV2021_ChangeDetection_Top3)|\n| 2021 | 建筑物 | [慧眼“天智杯”人工智能挑战赛](https:\u002F\u002Frsaicp.com\u002Fportal\u002FcontestList) |可见光建筑智能变化检测| 5,000 | 1,024×1,024 | 0.5-0.7m |-|\n| 2020 | 土地覆盖 | [商汤科技首届AI遥感解译大赛](https:\u002F\u002Fsenseearth-cloud.com\u002F) |变化检测|4,662 | 512×512 | 0.5-3m |[第一名解决方案](https:\u002F\u002Fgithub.com\u002FLiheYoung\u002FSenseEarth2020-ChangeDetection)|\n| 2020 | 土地覆盖 | [SpaceNet 7: 多时相城市发展挑战](https:\u002F\u002Fmedium.com\u002Fthe-downlinq\u002Fthe-spacenet-7-multi-temporal-urban-development-challenge-dataset-release-9e6e5f65c8d5) | 多时相城市发展挑战 |-|1,024×1,024| 4m |[解决方案](https:\u002F\u002Fgithub.com\u002FSpaceNetChallenge\u002FSpaceNet7_Multi-Temporal_Solutions), [数据集论文](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2021\u002Fpapers\u002FVan_Etten_The_Multi-Temporal_Urban_Development_SpaceNet_Dataset_CVPR_2021_paper.pdf)|\n| 2019 | 建筑物 | [xView2挑战赛](https:\u002F\u002Fxview2.org\u002Fdataset) (或xBD) | 建筑物损伤评估 | 11,034 | 1,024×1,024 | - |[数据集论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.09296)|\n\n\n# 用于灾害响应的卫星数据资源\n\n| 名称 | 描述 |\n| --- | --- | \n|[Maxar开放数据计划](https:\u002F\u002Fwww.maxar.com\u002Fopen-data)  |Maxar开放数据计划为选定的重大突发危机提供灾前和灾后卫星影像（来自WorldView-3及其他传感器），并附带众包损伤评估。|\n|[吉林一号资源库](https:\u002F\u002Fwww.jl1mall.com\u002Fresrepo\u002F?fromUrl=https:\u002F\u002Fwww.jl1mall.com\u002Fedu)|提供高分辨率卫星影像和专题数据，支持自然灾害监测、农业估产、生态环境保护、水利管理及应急响应等多领域应用。部分数据集仅限教育认证用户。|\n|[Planet灾害数据集](https:\u002F\u002Fwww.planet.com\u002Fdisasterdata\u002F) |Planet为重大灾害事件提供精选影像，包括大地震、洪水、风暴、野火以及人为灾害。用户需填写申请表以获得访问权限。|\n|[国际宪章：空间与重大灾害](https:\u002F\u002Fdisasterscharter.org\u002F)|针对各类全球性灾害，提供灾害测绘结果和分析报告，但不直接提供原始卫星影像。|\n\n\n# 更多资源\n\n| 名称 | 描述 |\n| --- | --- | \n|[Hansen全球森林变化](https:\u002F\u002Fglad.earthengine.app\u002Fview\u002Fglobal-forest-change) ([GEE数据集](https:\u002F\u002Fdevelopers.google.com\u002Fearth-engine\u002Fdatasets\u002Fcatalog\u002FUMD_hansen_global_forest_change_2023_v1_11))|以30米分辨率发布的年度全球林木覆盖损失与增长地图（2000年至今），广泛用作森林变化检测研究的地面真值标签和评估数据。由马里兰大学GLAD实验室制作。全分辨率GeoTIFF文件也可通过[earthenginepartners.appspot.com](https:\u002F\u002Fearthenginepartners.appspot.com\u002Fscience-2013-global-forest\u002Fdownload_v1.11.html)获取。|\n|[daifeng2016\u002F光学遥感数据集与方法大全](https:\u002F\u002Fgithub.com\u002Fdaifeng2016\u002FAwesome-Optical-Remote-Sensing-Datasets-and-Methods?tab=readme-ov-file)|该仓库旨在总结最新的光学遥感数据集和方法，这些内容在综述文章《光学遥感影像的深度学习变化检测技术：现状、展望与挑战》中有所提及，发表于[JAG2025](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS1569843224006381)。|\n|[MinZHANG-WHU\u002F变化检测综述](https:\u002F\u002Fgithub.com\u002FMinZHANG-WHU\u002FChange-Detection-Review)|一份关于变化检测方法的综述，包含代码和用于深度学习的公开数据集。摘自论文《基于人工智能的变化检测：现状与挑战》，发表于[RS2020](https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F12\u002F10\u002F1688)。|\n|[DoongLi\u002F场景变化检测大全](https:\u002F\u002Fgithub.com\u002FDoongLi\u002FAwesome-Scene-Change-Detection)|该仓库汇集了关于场景变化检测的全面资源，包括论文、视频、代码和相关网站。尽管许多变化检测研究聚焦于遥感领域，但本合集专门收录了基于街景场景的研究，并主要涵盖基于机器人视觉的方法（尤其是利用图像和点云数据）。|\n\n# 引用\n\n如果您在研究中使用了我们的项目，请考虑引用：\n\n```latex\n@misc{awesome_rscd_2019,\n    title={优秀的遥感变化检测资源},\n    author={优秀的遥感变化检测资源贡献者},\n    howpublished = {\\url{https:\u002F\u002Fgithub.com\u002Fwenhwu\u002Fawesome-remote-sensing-change-detection}},\n    year={2019}\n}\n```","# Awesome Remote Sensing Change Detection 快速上手指南\n\n`awesome-remote-sensing-change-detection` 是一个全面的遥感变化检测资源合集，汇集了最新的数据集、工具、算法模型（包括基础模型、扩散模型、Transformer 和 CNN）、综述论文及竞赛信息。本指南将帮助你快速利用该仓库中的资源开始研究或开发。\n\n## 环境准备\n\n在开始之前，请确保你的开发环境满足以下基本要求：\n\n*   **操作系统**: Linux (推荐 Ubuntu 20.04+), macOS 或 Windows (建议配合 WSL2 使用)。\n*   **编程语言**: Python 3.8 或更高版本。\n*   **硬件要求**: 建议配备 NVIDIA GPU (显存 ≥ 8GB) 以运行深度学习模型；若仅进行数据浏览或传统方法测试，CPU 即可。\n*   **前置依赖**:\n    *   Git (用于克隆仓库)\n    *   CUDA Toolkit (如需使用 GPU 加速，版本需与 PyTorch\u002FTensorFlow 匹配)\n    *   常用科学计算库：`numpy`, `pandas`, `matplotlib`, `opencv-python`\n\n## 安装步骤\n\n该项目本身是一个资源列表（Awesome List），不包含单一的可安装软件包。你需要克隆仓库并针对你感兴趣的具体数据集或算法代码进行独立配置。\n\n### 1. 克隆项目仓库\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fwenhwu\u002Fawesome-remote-sensing-change-detection.git\ncd awesome-remote-sensing-change-detection\n```\n\n### 2. 配置具体任务环境\n\n由于仓库涵盖了多种方法（如 Transformers, CNNs, Diffusion Models），请根据 `README.md` 中 **[Methods](#methods)** 章节链接到的具体子项目仓库进行安装。\n\n**通用深度学习环境搭建示例（基于 PyTorch）：**\n\n建议使用国内镜像源（如清华源）加速依赖安装。\n\n```bash\n# 创建虚拟环境\npython -m venv rs_cd_env\nsource rs_cd_env\u002Fbin\u002Factivate  # Windows 用户请使用: rs_cd_env\\Scripts\\activate\n\n# 安装 PyTorch (以 CUDA 11.8 为例，使用清华镜像)\npip install torch torchvision torchaudio --index-url https:\u002F\u002Fdownload.pytorch.org\u002Fwhl\u002Fcu118\n\n# 安装通用遥感处理依赖\npip install rasterio geopandas scikit-image albumentations -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n```\n\n> **注意**: 具体的模型代码（如 `ChangeFormer`, `BIT`, `SNUNet` 等）通常位于外部链接的独立 GitHub 仓库中。请点击主仓库表格中的 \"Source\" 或 \"Publication\" 链接跳转至对应项目，遵循其各自的 `requirements.txt` 进行安装。\n\n## 基本使用\n\n本仓库的核心价值在于提供**数据集索引**和**算法入口**。以下是典型的使用流程：\n\n### 1. 获取数据集\n\n在 **[Datasets](#datasets)** 部分查找适合你任务的数据集（例如建筑物变化检测 `LEVIR-CD` 或语义变化检测 `DSIFN-CD`）。\n\n*   **示例**: 下载 `LEVIR-CD` 数据集\n    ```bash\n    # 大多数数据集需要访问其官方 GitHub 页面或 Google Drive 链接下载\n    # 此处以克隆一个典型的包含数据加载器的子项目为例\n    git clone https:\u002F\u002Fgithub.com\u002FS2Looking\u002FDataset.git levir_cd_data\n    ```\n    *下载后，请按照各数据集文档说明整理目录结构（通常分为 `A`, `B`, `label` 文件夹）。*\n\n### 2. 运行基准模型\n\n找到你感兴趣的算法链接（例如在 **[Transformers](#transformers)** 类别下），克隆其代码库并运行推理或训练脚本。\n\n*   **示例**: 使用某个基于 Transformer 的变化检测模型进行预测\n    ```bash\n    # 假设已克隆具体算法仓库 algorithm_repo\n    cd algorithm_repo\n    \n    # 安装该算法特定依赖\n    pip install -r requirements.txt -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n\n    # 运行测试脚本 (具体命令视具体仓库而定，以下为通用示意)\n    python test.py --checkpoint_path pretrained_model.pth \\\n                   --data_root ..\u002Flevir_cd_data\u002Ftest \\\n                   --save_dir .\u002Fresults\n    ```\n\n### 3. 探索更多资源\n\n*   **综述论文**: 查阅 **[Review Papers](#review-papers)** 了解领域最新动态。\n*   **灾难响应**: 若关注灾害评估，参考 **[Satellite Data Resources for Disaster Response](#satellite-data-resources-for-disaster-response)** 获取实时数据源。\n*   **竞赛**: 关注 **[Competitions](#competitions)** 部分以获取高质量标注数据和评测基准。\n\n通过组合本仓库提供的数据集与前沿算法代码，你可以快速构建并验证自己的遥感变化检测方案。","某省级自然资源监测中心的研究团队正紧急开展年度违建拆除与耕地恢复情况的遥感核查工作，需要在短时间内处理全省高分辨率卫星影像。\n\n### 没有 awesome-remote-sensing-change-detection 时\n- **数据筛选耗时巨大**：团队需在 Google Scholar、GitHub 和各类论坛中手动搜索分散的数据集，难以快速找到适合中国地区高分辨率（如 0.5m）且标注精细的“耕地”或“建筑”变化检测数据。\n- **算法选型盲目低效**：面对层出不穷的深度学习模型（如 Transformer、扩散模型），缺乏系统的对比综述，只能凭经验盲目尝试旧版 CNN 网络，导致小目标漏检率高。\n- **复现门槛极高**：找到的论文往往缺少开源代码或依赖环境复杂，研究人员需花费数周时间重新编写数据预处理脚本，严重拖慢项目进度。\n- **灾害响应滞后**：在突发洪涝灾害评估中，因无法即时获取专门的灾害损毁评估（DDA）数据集资源，导致灾情分析报告延迟提交。\n\n### 使用 awesome-remote-sensing-change-detection 后\n- **一站式获取精准数据**：直接通过目录锁定针对中国区域（如厦门、福州）的 0.5m 分辨率耕地变化数据集，以及全球范围的 WHU-GCD 等高质量数据，数据准备时间从数周缩短至半天。\n- **科学匹配前沿模型**：依据整理的“基础模型”、“扩散模型”及\"Transformer\"分类列表，快速定位到最适合建筑物细粒度变化的 SOTA 算法，显著提升了违建识别的准确率。\n- **代码复用加速落地**：利用列表中提供的官方工具链接和开源实现，团队直接复用成熟的预处理管道和训练框架，将模型部署周期压缩了 70%。\n- **应急资源即时调用**：通过“灾害响应卫星数据资源”专区，迅速接入专为灾后评估设计的数据集与竞赛方案，实现了灾情的当日监测与上报。\n\nawesome-remote-sensing-change-detection 将原本碎片化的科研资源整合为标准化引擎，让遥感变化检测从“大海捞针”式的探索转变为高效精准的工业化流程。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fwenhwu_awesome-remote-sensing-change-detection_040e68f0.png","wenhwu",null,"https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fwenhwu_6707b327.png","what I can not create , I do not understand","wenhwu@126.com","https:\u002F\u002Fgithub.com\u002Fwenhwu",2166,391,"2026-04-02T13:17:17",5,"","未说明",{"notes":89,"python":87,"dependencies":90},"该仓库（awesome-remote-sensing-change-detection）是一个遥感变化检测领域的资源汇编列表（Awesome List），主要包含数据集、工具、方法论文和竞赛信息的链接索引，本身不是一个可直接运行的软件工具或代码库，因此 README 中未提供具体的操作系统、GPU、内存、Python 版本或依赖库等运行环境需求。用户需根据列表中链接的具体子项目（如特定的 GitHub 代码库）去查阅其各自的安装说明。",[],[13,51],[93,94,95,96,97],"awesome","change-detection","remote-sensing","dataset","deep-learning","2026-03-27T02:49:30.150509","2026-04-06T05:44:17.449141",[101,106,111,116,121,126],{"id":102,"question_zh":103,"answer_zh":104,"source_url":105},10952,"如何获取用于变化检测的训练数据集？","深度学习需要大量训练样本，理论上越多越好。实验中约 1 对高分二号影像（2 幅，约 10000×6000 大小）即可实现不错效果。不同数据集定义不同，需结合具体需求勾绘。可参考广东政务数据创新大赛的智能算法赛数据集（链接：https:\u002F\u002Fpan.baidu.com\u002Fs\u002F1tjw_akfpDjxLo4s4RKwCDw，提取码：8r58）。此外，武汉大学也有相关变化检测数据集资源。","https:\u002F\u002Fgithub.com\u002Fwenhwu\u002Fawesome-remote-sensing-change-detection\u002Fissues\u002F4",{"id":107,"question_zh":108,"answer_zh":109,"source_url":110},10953,"PCC（Post Classification Comparison）有现成的代码吗？","PCC 即“分类后变化检测”，是一种思路而非特定算法，任何分类方法均可套用。文中提到 PCC 高度依赖分类图质量，个体误差会累积导致结果噪声。可参考 GlobWetlandAfrica 项目中的实现代码：https:\u002F\u002Fgithub.com\u002FGlobWetlandAfrica\u002FGWA_scripts\u002Fblob\u002F526c9cd0fdccf1b2ab66105823133a151583f1cb\u002Fscripts\u002FGWA_TBX\u002FpostclassificationComparison.py。但需注意该代码可能仅为示例，实用性有限。","https:\u002F\u002Fgithub.com\u002Fwenhwu\u002Fawesome-remote-sensing-change-detection\u002Fissues\u002F2",{"id":112,"question_zh":113,"answer_zh":114,"source_url":115},10954,"SMARS 数据集下载链接失效或文件大小不符怎么办？","若下载的文件体积远小于宣称的 9.0 GB，可能是压缩所致。建议尝试解压文件，因为其中的分类图文件压缩率很高，解压后应接近标称大小。如仍不符，可能发布版本非完整数据集，需联系原作者确认。","https:\u002F\u002Fgithub.com\u002Fwenhwu\u002Fawesome-remote-sensing-change-detection\u002Fissues\u002F27",{"id":117,"question_zh":118,"answer_zh":119,"source_url":120},10955,"无法从官方渠道下载 HRSCD 数据集的 2006 年影像怎么办？","HRSCD 的 2006 年影像受不可再分发许可限制，需从 IGN 官网下载（https:\u002F\u002Fgeoservices.ign.fr\u002Fdocumentation\u002Fdiffusion\u002Ftelechargement-donnees-libres.html#bd-ortho-50-cm 或 https:\u002F\u002Fwww.geoportail.gouv.fr\u002Fcarte），所需文件包括 BD ORTHO® 50 cm, D 14 - CALVADOS, 2005 和 D 35 - ILLE-ET-VILLAINE, 2006。如下载困难，可联系作者 Rodrigo Caye Daudt，其最新邮箱为 rodrigo.cayedaudt@geod.baug.ethz.ch，或个人网站 https:\u002F\u002Frcdaudt.github.io\u002F 提供的联系方式。","https:\u002F\u002Fgithub.com\u002Fwenhwu\u002Fawesome-remote-sensing-change-detection\u002Fissues\u002F10",{"id":122,"question_zh":123,"answer_zh":124,"source_url":125},10956,"是否有 SAR 船舶变化检测的数据集或方法？","目前几乎没有公开的 SAR 船舶变化检测数据集，且该任务本身意义有限，因为船舶并非地表固定物体（如建筑物），更适合做“船舶目标检测”或“跟踪”而非“变化检测”。推荐参考 Airbus Ship Detection Challenge（https:\u002F\u002Fwww.kaggle.com\u002Fc\u002Fairbus-ship-detection）或 CAESAR-Radi\u002FSAR-Ship-Dataset（https:\u002F\u002Fgithub.com\u002FCAESAR-Radi\u002FSAR-Ship-Dataset）。若仍需 SAR 变化检测方法，可查阅论文《A Survey of Change Detection Methods Based on Remote Sensing Images for Multi-Source and Multi-Objective Scenarios》（https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F12\u002F15\u002F2460）及其引用的数据集。","https:\u002F\u002Fgithub.com\u002Fwenhwu\u002Fawesome-remote-sensing-change-detection\u002Fissues\u002F8",{"id":127,"question_zh":128,"answer_zh":129,"source_url":130},10957,"如何将新的遥感变化检测研究成果添加到本仓库列表中？","欢迎提交 Pull Request 将您的项目加入数据集\u002F代码列表。为保持一致性，请使用统一的表格格式，例如：\n|年份|任务类型|地物类别|数据集链接|论文链接|数据来源|图像数量|分辨率|空间分辨率|地区|类别数|\n示例行：\n|2026|SCD+BCD|Building|[FOTBCD-Binary;FOTBCD-Instances](https:\u002F\u002Fgithub.com\u002Fabdelpy\u002FFOTBCD-datasets)|[arXiv2026](https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.22596)|IGN|27,871; 4000|512 × 512|0.2m|France|2; 3|\n请将新条目添加至 README.md 文件中。","https:\u002F\u002Fgithub.com\u002Fwenhwu\u002Fawesome-remote-sensing-change-detection\u002Fissues\u002F31",[132],{"id":133,"version":134,"summary_zh":135,"released_at":136},53419,"v1.0","🎉 **首次发布！**\n\n本次 `v1.0` 版本标志着 `awesome-remote-sensing-change-detection` 仓库的首个正式快照。\n\n**本次发布的主要内容：**\n\n* **基础框架：** 该版本包含大量初始数据集、代码及与遥感变化检测相关的竞赛资源。\n* **已知问题：** 本版本仍处于“开发中”状态。格式不统一，内容缺乏清晰的层级结构，在现阶段更像是一次数据的简单汇集，而非精心整理的列表。\n\n**未来计划：**\n\n我们接下来的重点工作是重构和优化这份列表。后续版本将聚焦于：\n* 统一所有条目的格式；\n* 构建逻辑清晰的分类体系（例如按数据集、按方法等）；\n* 为每项资源添加更加简洁明了的说明性注释。\n\n我们诚挚欢迎各位贡献者一起完善这份精彩的资源清单！","2025-09-16T15:38:20"]