[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-jason718--awesome-self-supervised-learning":3,"tool-jason718--awesome-self-supervised-learning":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":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":80,"owner_email":78,"owner_twitter":78,"owner_website":78,"owner_url":81,"languages":78,"stars":82,"forks":83,"last_commit_at":84,"license":78,"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":78,"oss_zip_packed_at":78,"status":16,"created_at":100,"updated_at":101,"faqs":102,"releases":103},3289,"jason718\u002Fawesome-self-supervised-learning","awesome-self-supervised-learning","A curated list of awesome self-supervised methods","awesome-self-supervised-learning 是一个精心整理的自监督学习资源清单，旨在为人工智能社区提供一站式的学习与参考入口。自监督学习是当前 AI 领域极具潜力的方向，它能让模型在无需大量人工标注数据的情况下，通过挖掘数据自身的内在结构进行高效训练，从而解决传统监督学习中数据标注成本高昂且稀缺的痛点。\n\n这份清单涵盖了从基础理论推导到多领域应用的全方位内容，包括计算机视觉、自然语言处理、机器人学、语音识别及时间序列分析等。其独特亮点在于不仅收录了经典的学术论文和开源代码链接，还系统性地梳理了对比学习等核心方法的理论分析，并汇集了相关的技术演讲、学位论文及博客文章，帮助使用者深入理解“为何自监督学习是 AI 未来的基石”。\n\nawesome-self-supervised-learning 非常适合 AI 研究人员、算法工程师以及希望深入探索前沿技术的开发者使用。对于想要快速掌握该领域发展脉络、寻找最新研究灵感或复现经典算法的用户来说，这是一个极具价值的导航工具，能帮助大家高效地站在巨人的肩膀上开展创新工作。","# Awesome Self-Supervised Learning[![Awesome](https:\u002F\u002Fawesome.re\u002Fbadge.svg)](https:\u002F\u002Fawesome.re)\n\nA curated list of awesome Self-Supervised Learning resources. Inspired by [awesome-deep-vision](https:\u002F\u002Fgithub.com\u002Fkjw0612\u002Fawesome-deep-vision), [awesome-adversarial-machine-learning](https:\u002F\u002Fgithub.com\u002Fyenchenlin\u002Fawesome-adversarial-machine-learning), [awesome-deep-learning-papers](https:\u002F\u002Fgithub.com\u002Fterryum\u002Fawesome-deep-learning-papers), and [awesome-architecture-search](https:\u002F\u002Fgithub.com\u002Fmarkdtw\u002Fawesome-architecture-search)\n\n#### Why Self-Supervised?\nSelf-Supervised Learning has become an exciting direction in AI community. \n  - Jitendra Malik: \"Supervision is the opium of the AI researcher\"\n  - Alyosha Efros: \"The AI revolution will not be supervised\"\n  - Yann LeCun: \"self-supervised learning is the cake, supervised learning is the icing on the cake, reinforcement learning is the cherry on the cake\"\n\n## Contributing\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjason718_awesome-self-supervised-learning_readme_7a9f4b7eebd0.jpg\" alt=\"We Need You!\">\n\u003C\u002Fp>\n\nPlease help contribute this list by [pull request](https:\u002F\u002Fgithub.com\u002Fjason718\u002FAwesome-Self-Supervised-Learning\u002Fpulls)\n\nMarkdown format:\n```markdown\n- Paper Name. \n  [[pdf]](link) \n  [[code]](link)\n  - Author 1, Author 2, and Author 3. *Conference Year*\n```\n\n## Table of Contents\n- [Theory](#theory)\n- [Computer Vision (CV)](#computer-vision)\n  - [Survey](#survey)\n  - [Image Representation Learning](#image-representation-learning)\n  - [Video Representation Learning](#video-representation-learning)\n  - [3D Feature Learning](#3D-feature-learning)\n  - [Geometry](#geometry)\n  - [Audio](#audio)\n  - [Others](#others)\n- [Machine Learning](#machine-learning)\n  - [Reinforcement Learning](#reinforcement-learning)\n  - [Recommendation Systems](#recommendation-systems)\n- [Robotics](#robotics)  \n- [Natural Language Processing (NLP)](#nlp)\n- [Automatic Speech Recognition (ASR)](#asr)\n- [Time-Series](#Time-Series)\n- [Graph](#graph)\n- [Talks](#talks)\n- [Thesis](#thesis)\n- [Blog](#blog)\n\n\n\n## Theory\n\n#### 2019\n-   A Theoretical Analysis of Contrastive Unsupervised Representation Learning.\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1902.09229.pdf)\n    -   Sanjeev Arora, Hrishikesh Khandeparkar, Mikhail Khodak, Orestis Plevrakis, and Nikunj Saunshi. *ICML 2019*\n#### 2020\n-   Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere.\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2005.10242)\n    -   Tongzhou Wang, Phillip Isola. *ICML 2020*\n-   Understanding Self-supervised Learning with Dual Deep Networks.\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2010.00578.pdf)\n    -   Yuandong Tian, Lantao Yu, Xinlei Chen, and Surya Ganguli.\n-   For self-supervised learning, Rationality implies generalization, provably.\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2010.08508.pdf)\n    -   Yamini Bansal, Gal Kaplun, and Boaz Barak.\n   \n#### 2021\n-   Towards the Generalization of Contrastive Self-Supervised Learning.\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2111.00743.pdf)\n    -   Weiran Huang, Mingyang Yi, and Xuyang Zhao.\n-   Understanding the Behaviour of Contrastive Loss.\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2012.09740.pdf)\n    -   Feng Wang and Huaping Liu. *CVPR 2021*\n-   Predicting What You Already Know Helps: Provable Self-Supervised Learning. \n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2008.01064.pdf)\n    -   Jason D. Lee, Qi Lei, Nikunj Saunshi, and Jiacheng Zhuo.\n-   Contrastive learning , multi-view redundancy , and linear models.\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2008.10150.pdf)\n    -   Christopher Tosh, Akshay Krishnamurthy, and Daniel Hsu.\n-   Contrastive Learning Inverts the Data Generating Process.\n    [[pdf]](Contrastive Learning Inverts the Data Generating Process)\n    -   Roland S. Zimmermann, Yash Sharma, Steffen Schneider, Matthias Bethge, Wieland Brendel. **ICML 2021**\n\n\n#### 2022\n-   Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant Functions.\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2103.03568.pdf)\n    -   Jiaye Teng, Weiran Huang, and Haowei He. *AISTATS 2022*\n\n#### 2023\n-   Can Pretext-Based Self-Supervised Learning Be Boosted by Downstream Data? A Theoretical Analysis.\n    [[pdf]](https:\u002F\u002Fopenreview.net\u002Fpdf?id=AjC0KBjiMu)\n    -   Daniel D. Johnson, Ayoub El Hanchi, Chris J. Maddison. *ICLR 2023*\n-   On the Stepwise Nature of Self-Supervised Learning.\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2303.15438)\n    -   James B. Simon, Maksis Knutins, Liu Ziyin, Daniel Geisz, Abraham J. Fetterman, Joshua Albrecht. *ICML 2023*\n-   What shapes the loss landscape of self supervised learning?\n    [[pdf]](https:\u002F\u002Fopenreview.net\u002Fpdf?id=3zSn48RUO8M)\n    -   Liu Ziyin, Ekdeep Singh Lubana, Masahito Ueda, Hidenori Tanaka. *ICLR 2023*\n\n\n#### 2024  \n-   Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses.\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2405.18045)\n    [[code]](https:\u002F\u002Fgithub.com\u002Fpakoromilas\u002FDHEL-KCL)\n    -   Panagiotis Koromilas, Giorgos Bouritsas, Theodoros Giannakopoulos, Mihalis Nicolaou, Yannis Panagakis. *ICML 2024*\n-   Matrix Information Theory for Self-Supervised Learning.\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2305.17326)\n    -  Yifan Zhang, Zhiquan Tan, Jingqin Yang, Weiran Huang, Yang Yuan. *ICML 2024*\n-   Information Flow in Self-Supervised Learning.\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2309.17281)\n    -  Zhiquan Tan, Jingqin Yang, Weiran Huang, Yang Yuan, Yifan Zhang. *ICML 2024*\n\n\n       \n## Computer Vision\n### Survey\n- Contrastive Representation Learning: A Framework and Review\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.05113)\n  - Phuc H. Le-Khac, Graham Healy, Alan F. Smeaton. *IEEE Access 2020*\n\n- A Survey on Contrastive Self-supervised Learning\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2011.00362.pdf)\n  - Ashish Jaiswal, Ashwin R Babu, Mohammad Z Zadeh, Debapriya Banerjee, Fillia Makedon\n\n- Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1902.06162.pdf)\n  - Longlong Jing and Yingli Tian. *T-PAMI 2020*\n\n- Self-supervised Learning: Generative or Contrastive\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.08218.pdf)\n  - Xiao Liu, Fanjin Zhang, Zhenyu Hou, Li Mian, Zhaoyu Wang, Jing Zhang, Jie Tang. *TKDE 2021*\n\n- Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Training\n  [[pdf]](https:\u002F\u002Fopenreview.net\u002Fpdf?id=Ma25S4ludQ)\n  - Utku Ozbulak, Hyun Jung Lee, Beril Boga, Esla Timothy Anzaku, Ho-min Park, Arnout Van Messem, Wesley De Neve, Joris Vankerschaver. *TMLR 2023*\n\n\n### Image Representation Learning\n\n#### Benchmark code\n- FAIR Self-Supervision Benchmark [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.01235) [[repo]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Ffair_self_supervision_benchmark): various benchmark (and legacy) tasks for evaluating quality of visual representations learned by various self-supervision approaches.\n\n- How Well Do Self-Supervised Models Transfer? [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.13377) [[repo]](https:\u002F\u002Fgithub.com\u002Flinusericsson\u002Fssl-transfer): A benchmark for evaluating self-supervision consisting of many-shot\u002Ffew-shot recognition, object detection, surface normal estimation and semantic segmentation.\n\n#### 2015\n- Unsupervised Visual Representation Learning by Context Prediction.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1505.05192)\n  [[code]](http:\u002F\u002Fgraphics.cs.cmu.edu\u002Fprojects\u002FdeepContext\u002F)\n  - Doersch, Carl and Gupta, Abhinav and Efros, Alexei A. *ICCV 2015*\n\n- Unsupervised Learning of Visual Representations using Videos.\n  [[pdf]](http:\u002F\u002Fwww.cs.cmu.edu\u002F~xiaolonw\u002Fpapers\u002Funsupervised_video.pdf) \n  [[code]](http:\u002F\u002Fwww.cs.cmu.edu\u002F~xiaolonw\u002Funsupervise.html)\n  - Wang, Xiaolong and Gupta, Abhinav. *ICCV 2015*\n\n- Learning to See by Moving. \n  [[pdf]](http:\u002F\u002Farxiv.org\u002Fabs\u002F1505.01596)\n  [[code]](https:\u002F\u002Fpeople.eecs.berkeley.edu\u002F~pulkitag\u002Flsm\u002Flsm.html)\n  - Agrawal, Pulkit and Carreira, Joao and Malik, Jitendra. *ICCV 2015*\n\n- Learning image representations tied to ego-motion.\n  [[pdf]](http:\u002F\u002Fvision.cs.utexas.edu\u002Fprojects\u002Fegoequiv\u002Fijcv_bestpaper_specialissue_egoequiv.pdf) \n  [[code]](http:\u002F\u002Fvision.cs.utexas.edu\u002Fprojects\u002Fegoequiv\u002F)\n  - Jayaraman, Dinesh and Grauman, Kristen. *ICCV 2015*\n\n#### 2016\n- Joint Unsupervised Learning of Deep Representations and Image Clusters. \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1604.03628.pdf) \n  [[code-torch]](https:\u002F\u002Fgithub.com\u002Fjwyang\u002FJULE.torch)\n  [[code-caffe]](https:\u002F\u002Fgithub.com\u002Fjwyang\u002FJULE-Caffe)\n  - Jianwei Yang, Devi Parikh, Dhruv Batra. *CVPR 2016*\n  \n- Unsupervised Deep Embedding for Clustering Analysis.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1511.06335.pdf) \n  [[code]](https:\u002F\u002Fgithub.com\u002Fpiiswrong\u002Fdec)\n  - Junyuan Xie, Ross Girshick, and Ali Farhadi. *ICML 2016*\n  \n- Slow and steady feature analysis: higher order temporal coherence in video. \n  [[pdf]](http:\u002F\u002Fvision.cs.utexas.edu\u002Fprojects\u002Fslowsteady\u002Fcvpr16.pdf)\n  - Jayaraman, Dinesh and Grauman, Kristen. *CVPR 2016*\n\n- Context Encoders: Feature Learning by Inpainting. \n  [[pdf]](https:\u002F\u002Fpeople.eecs.berkeley.edu\u002F~pathak\u002Fpapers\u002Fcvpr16.pdf)\n  [[code]](https:\u002F\u002Fpeople.eecs.berkeley.edu\u002F~pathak\u002Fcontext_encoder\u002F)\n  - Pathak, Deepak and  Krahenbuhl, Philipp and Donahue, Jeff and Darrell, Trevor and Efros, Alexei A. *CVPR 2016*\n\n- Colorful Image Colorization.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1603.08511)\n  [[code]](http:\u002F\u002Frichzhang.github.io\u002Fcolorization\u002F)\n  - Zhang, Richard and Isola, Phillip and Efros, Alexei A. *ECCV 2016*\n\n- Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles.\n  [[pdf]](http:\u002F\u002Farxiv.org\u002Fabs\u002F1603.09246)\n  [[code]](http:\u002F\u002Fwww.cvg.unibe.ch\u002Fresearch\u002FJigsawPuzzleSolver.html)\n  - Noroozi, Mehdi and Favaro, Paolo. *ECCV 2016*\n\n- Ambient Sound Provides Supervision for Visual Learning.\n  [[pdf]](http:\u002F\u002Farxiv.org\u002Fpdf\u002F1608.07017) \n  [[code]](http:\u002F\u002Fandrewowens.com\u002Fambient\u002Findex.html)\n  - Owens, Andrew and Wu, Jiajun and McDermott, Josh and Freeman, William and Torralba, Antonio. *ECCV 2016*\n\n- Learning Representations for Automatic Colorization. \n  [[pdf]](http:\u002F\u002Farxiv.org\u002Fpdf\u002F1603.06668.pdf)\n  [[code]](http:\u002F\u002Fpeople.cs.uchicago.edu\u002F~larsson\u002Fcolorization\u002F)\n  - Larsson, Gustav and Maire, Michael and Shakhnarovich, Gregory. *ECCV 2016*\n\n-   Unsupervised Visual Representation Learning by Graph-based Consistent Constraints.\n    [\\[pdf\\]](http:\u002F\u002Ffaculty.ucmerced.edu\u002Fmhyang\u002Fpapers\u002Feccv16_feature_learning.pdf)\n    [\\[code\\]](https:\u002F\u002Fgithub.com\u002Fdongli12\u002FFeatureLearning)\n    -   Li, Dong and Hung, Wei-Chih and Huang, Jia-Bin and Wang, Shengjin and Ahuja, Narendra and Yang, Ming-Hsuan. *ECCV 2016*\n\n#### 2017\n- Adversarial Feature Learning. \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1605.09782.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fjeffdonahue\u002Fbigan)\n  - Donahue, Jeff and Krahenbuhl, Philipp and Darrell, Trevor. *ICLR 2017*\n  \n- Self-supervised learning of visual features through embedding images into text topic spaces.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1705.08631.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Flluisgomez\u002FTextTopicNet)\n  - L. Gomez* and Y. Patel* and M. Rusiñol and D. Karatzas and C.V. Jawahar. *CVPR 2017*\n  \n- Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1611.09842) \n  [[code]](https:\u002F\u002Fgithub.com\u002Frichzhang\u002Fsplitbrainauto)\n  - Zhang, Richard and Isola, Phillip and Efros, Alexei A. *CVPR 2017*\n\n- Learning Features by Watching Objects Move.\n  [[pdf]](https:\u002F\u002Fpeople.eecs.berkeley.edu\u002F~pathak\u002Fpapers\u002Fcvpr17.pdf) \n  [[code]](https:\u002F\u002Fpeople.eecs.berkeley.edu\u002F~pathak\u002Funsupervised_video\u002F)\n  - Pathak, Deepak and Girshick, Ross and Dollar, Piotr and  Darrell, Trevor and Hariharan, Bharath. *CVPR 2017*\n  \n- Colorization as a Proxy Task for Visual Understanding. \n  [[pdf]](http:\u002F\u002Farxiv.org\u002Fabs\u002F1703.04044) \n  [[code]](http:\u002F\u002Fpeople.cs.uchicago.edu\u002F~larsson\u002Fcolor-proxy\u002F)\n  - Larsson, Gustav and Maire, Michael and Shakhnarovich, Gregory. *CVPR 2017*\n\n-   DeepPermNet: Visual Permutation Learning.\n    [\\[pdf\\]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1704.02729.pdf)\n    [\\[code\\]](https:\u002F\u002Fgithub.com\u002Frfsantacruz\u002Fdeep-perm-net)\n    -   Cruz, Rodrigo Santa and Fernando, Basura and Cherian, Anoop and Gould, Stephen. *CVPR 2017*\n\n- Unsupervised Learning by Predicting Noise.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1704.05310) \n  [[code]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fnoise-as-targets)\n  - Bojanowski, Piotr and Joulin, Armand. *ICML 2017*\n\n- Multi-task Self-Supervised Visual Learning. \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1708.07860)\n  - Doersch, Carl and Zisserman, Andrew. *ICCV 2017*\n\n- Representation Learning by Learning to Count.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1708.06734)\n  - Noroozi, Mehdi and Pirsiavash, Hamed and Favaro, Paolo. *ICCV 2017*\n\n- Transitive Invariance for Self-supervised Visual Representation Learning.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1708.02901.pdf)\n  - Wang, Xiaolong and He, Kaiming and Gupta, Abhinav. *ICCV 2017*\n\n- Look, Listen and Learn. \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1705.08168.pdf)\n  - Relja, Arandjelovic and Zisserman, Andrew. *ICCV 2017*\n\n- Unsupervised Representation Learning by Sorting Sequences. \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1708.01246.pdf) \n  [[code]](https:\u002F\u002Fgithub.com\u002FHsinYingLee\u002FOPN)\n  - Hsin-Ying Lee, Jia-Bin Huang, Maneesh Kumar Singh, and Ming-Hsuan Yang. *ICCV 2017*\n\n#### 2018\n- Unsupervised Feature Learning via Non-parameteric Instance Discrimination\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1805.01978.pdf) \n  [[code]](https:\u002F\u002Fgithub.com\u002Fzhirongw\u002Flemniscate.pytorch)\n  - Zhirong Wu, Yuanjun Xiong and X Yu Stella and Dahua Lin. *CVPR 2018*\n\n- Learning Image Representations by Completing Damaged Jigsaw Puzzles. \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1802.01880.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002FMehdiNoroozi\u002FJigsawPuzzleSolver)\n  - Kim, Dahun and Cho, Donghyeon and Yoo, Donggeun and Kweon, In So. *WACV 2018*\n  \n- Unsupervised Representation Learning by Predicting Image Rotations. \n  [[pdf]](https:\u002F\u002Fopenreview.net\u002Fforum?id=S1v4N2l0-)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fgidariss\u002FFeatureLearningRotNet)\n  - Spyros Gidaris and Praveer Singh and Nikos Komodakis. *ICLR 2018*\n  \n- Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity Regularization. \n  [[pdf]](https:\u002F\u002Fopenreview.net\u002Fpdf?id=HkMvEOlAb) \n  [[code]](https:\u002F\u002Fgithub.com\u002Fozcell\u002FLALNets)\n  - Ozsel Kilinc and Ismail Uysal. *ICLR 2018*\n  \n- Improvements to context based self-supervised learning. \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1711.06379)\n  - Terrell Mundhenk and Daniel Ho and Barry Chen. *CVPR 2018*\n  \n- Self-Supervised Feature Learning by Learning to Spot Artifacts.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1806.05024.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fsjenni\u002FLearningToSpotArtifacts)\n  - Simon Jenni and Universität Bern and Paolo Favaro. *CVPR 2018*\n  \n- Boosting Self-Supervised Learning via Knowledge Transfer. \n  [[pdf]](https:\u002F\u002Fwww.csee.umbc.edu\u002F~hpirsiav\u002Fpapers\u002Ftransfer_cvpr18.pdf)\n  - Mehdi Noroozi and Ananth Vinjimoor and Paolo Favaro and Hamed Pirsiavash. *CVPR 2018*\n  \n- Cross-domain Self-supervised Multi-task Feature Learning Using Synthetic Imagery. \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1711.09082)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fjason718\u002Fgame-feature-learning)\n  - Zhongzheng Ren and Yong Jae Lee. *CVPR 2018*\n  \n- ShapeCodes: Self-Supervised Feature Learning by Lifting Views to Viewgrids.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.00505.pdf)\n  - Dinesh Jayaraman*, UC Berkeley; Ruohan Gao, University of Texas at Austin; Kristen Grauman. *ECCV 2018*\n\n- Deep Clustering for Unsupervised Learning of Visual Features\n    [[pdf]](https:\u002F\u002Fresearch.fb.com\u002Fwp-content\u002Fuploads\u002F2018\u002F09\u002FDeep-Clustering-for-Unsupervised-Learning-of-Visual-Features.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fdeepcluster)\n    - Mathilde Caron, Piotr Bojanowski, Armand Joulin, Matthijs Douze. *ECCV 2018*\n\n- Cross Pixel Optical-Flow Similarity for Self-Supervised Learning.\n  [[pdf]](http:\u002F\u002Fwww.robots.ox.ac.uk\u002F~vgg\u002Fpublications\u002F2018\u002FMahendran18\u002Fmahendran18.pdf)\n  - Aravindh Mahendran, James Thewlis, Andrea Vedaldi. *ACCV 2018*\n\n#### 2019\n- Representation Learning with Contrastive Predictive Coding.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1807.03748)\n  - Aaron van den Oord, Yazhe Li, Oriol Vinyals.\n\n- Self-Supervised Learning via Conditional Motion Propagation.\n  [[pdf]](\u003Chttps:\u002F\u002Farxiv.org\u002Fabs\u002F1903.11412>)\n  [[code]](https:\u002F\u002Fgithub.com\u002FXiaohangZhan\u002Fconditional-motion-propagation)\n  - Xiaohang Zhan, Xingang Pan, Ziwei Liu, Dahua Lin, and Chen Change Loy. *CVPR 2019*\n\n- Self-Supervised Representation Learning by Rotation Feature Decoupling.\n  [[pdf]](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_CVPR_2019\u002Fhtml\u002FFeng_Self-Supervised_Representation_Learning_by_Rotation_Feature_Decoupling_CVPR_2019_paper.html)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fphiliptheother\u002FFeatureDecoupling)\n  - Zeyu Feng; Chang Xu; Dacheng Tao. *CVPR 2019*\n\n- Revisiting Self-Supervised Visual Representation Learning.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1901.09005)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fgoogle\u002Frevisiting-self-supervised)\n  - Alexander Kolesnikov; Xiaohua Zhai; Lucas Beye. *CVPR 2019*\n  \n- Self-Supervised GANs via Auxiliary Rotation Loss. \n  [[pdf]](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_CVPR_2019\u002Fpapers\u002FChen_Self-Supervised_GANs_via_Auxiliary_Rotation_Loss_CVPR_2019_paper.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fvandit15\u002FSelf-Supervised-Gans-Pytorch)\n  - Ting Chen; Xiaohua Zhai; Marvin Ritter; Mario Lucic; Neil Houlsby. *CVPR 2019*\n\n- AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Data.\n  [[pdf]](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_CVPR_2019\u002Fpapers\u002FZhang_AET_vs._AED_Unsupervised_Representation_Learning_by_Auto-Encoding_Transformations_Rather_CVPR_2019_paper.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fmaple-research-lab\u002FAET)\n  - Liheng Zhang, Guo-Jun Qi, Liqiang Wang, Jiebo Luo. *CVPR 2019*\n\n- Unsupervised Deep Learning by Neighbourhood Discovery.\n  [[pdf]](http:\u002F\u002Fproceedings.mlr.press\u002Fv97\u002Fhuang19b.html).\n  [[code]](https:\u002F\u002Fgithub.com\u002FRaymond-sci\u002FAND).\n  - Jiabo Huang, Qi Dong, Shaogang Gong, Xiatian Zhu. *ICML 2019*\n  \n- Contrastive Multiview Coding.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.05849)\n  [[code]](https:\u002F\u002Fgithub.com\u002FHobbitLong\u002FCMC\u002F)\n  - Yonglong Tian and Dilip Krishnan and Phillip Isola.\n\n- Large Scale Adversarial Representation Learning.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1907.02544)\n  - Jeff Donahue, Karen Simonyan.\n\n- Learning Representations by Maximizing Mutual Information Across Views.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1906.00910)\n  [[code]](https:\u002F\u002Fgithub.com\u002FPhilip-Bachman\u002Famdim-public)\n  - Philip Bachman, R Devon Hjelm, William Buchwalter\n\n - Selfie: Self-supervised Pretraining for Image Embedding. \n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.02940) \n    - Trieu H. Trinh, Minh-Thang Luong, Quoc V. Le\n   \n - Data-Efficient Image Recognition with Contrastive Predictive Coding\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.09272)\n    - Olivier J. He ́naff, Ali Razavi, Carl Doersch, S. M. Ali Eslami, Aaron van den Oord\n\n - Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1906.12340)\n    [[code]](https:\u002F\u002Fgithub.com\u002Fhendrycks\u002Fss-ood)\n    - Dan Hendrycks, Mantas Mazeika, Saurav Kadavath, Dawn Song. *NeurIPS 2019*\n    \n - Boosting Few-Shot Visual Learning with Self-Supervision\n    [[pdf]](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ICCV_2019\u002Fpapers\u002FGidaris_Boosting_Few-Shot_Visual_Learning_With_Self-Supervision_ICCV_2019_paper.pdf)\n    - Pyros Gidaris, Andrei Bursuc, Nikos Komodakis, Patrick Pérez, and Matthieu Cord. *ICCV 2019*\n\n - Self-Supervised Generalisation with Meta Auxiliary Learning\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1901.08933.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002Florenmt\u002Fmaxl)\n    - Shikun Liu, Andrew J. Davison, Edward Johns. *NeurIPS 2019*\n\n - Wasserstein Dependency Measure for Representation Learning\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.11780.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002FSeongokRyu\u002Fmutual_information_and_self-supervised_learning\u002Ftree\u002Fmaster\u002Fpredictive_coding)\n    - Sherjil Ozair, Corey Lynch, Yoshua Bengio, Aaron van den Oord, Sergey Levine, Pierre Sermanet. *NeurIPS 2019*\n\n- Scaling and Benchmarking Self-Supervised Visual Representation Learning\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.01235)\n    [[code]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Ffair_self_supervision_benchmark)\n    - Priya Goyal, Dhruv Mahajan, Abhinav Gupta, Ishan Misra. *ICCV 2019*\n\n- Unsupervised Pre-Training of Image Features on Non-Curated Data\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1905.01278.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002FDeeperCluster)\n    - Mathilde Caron, Piotr Bojanowski, Julien Mairal, Armand Joulin. *ICCV 2019 Oral*\n\n- S4L: Self-Supervised Semi-Supervised Learning\n  [[pdf]](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ICCV_2019\u002Fpapers\u002FZhai_S4L_Self-Supervised_Semi-Supervised_Learning_ICCV_2019_paper.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fs4l)\n  - Xiaohua Zhai, Avital Oliver, Alexander Kolesnikov, Lucas Beyer. *ICCV 2019*\n\n- Self-supervised model adaptation for multimodal semantic segmentation. \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1808.03833) \n  [[code]](https:\u002F\u002Fgithub.com\u002FDeepSceneSeg\u002FSSMA)\n  - Abhinav Valada, Rohit Mohan, and Wolfram Burgard. *IJCV 2019*\n    \n#### 2020\n - A critical analysis of self-supervision, or what we can learn from a single image\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1904.13132)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fyukimasano\u002Flinear-probes)\n   - Yuki M. Asano, Christian Rupprecht, Andrea Vedaldi. *ICLR 2020*\n\n - On Mutual Information Maximization for Representation Learning\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1907.13625.pdf)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fgoogle-research\u002Ftree\u002Fmaster\u002Fmutual_information_representation_learning)\n   - Michael Tschannen, Josip Djolonga, Paul K. Rubenstein, Sylvain Gelly, Mario Lucic. *ICLR 2020*\n\n - Understanding the Limitations of Variational Mutual Information Estimators\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.06222)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fermongroup\u002Fsmile-mi-estimator)\n   - Jiaming Song, Stefano Ermon. *ICLR 2020*\n\n - Self-labelling via simultaneous clustering and representation learning\n   [[pdf]](https:\u002F\u002Fopenreview.net\u002Fpdf?id=Hyx-jyBFPr)\n   [[blogpost]](http:\u002F\u002Fwww.robots.ox.ac.uk\u002F~vgg\u002Fblog\u002Fself-labelling-via-simultaneous-clustering-and-representation-learning.html)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fyukimasano\u002Fself-label)\n   - Yuki Markus Asano, Christian Rupprecht, Andrea Vedaldi. *ICLR 2020 (Spotlight)*\n\n - Self-supervised Label Augmentation via Input Transformations\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.05872)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fhankook\u002FSLA)\n   - Hankook Lee, Sung Ju Hwang, Jinwoo Shin. *ICML 2020*\n\n - Automatic Shortcut Removal for Self-Supervised Representation Learning\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2002.08822.pdf)\n   - Matthias Minderer, Olivier Bachem, Neil Houlsby, Michael Tschannen\n\n - A Simple Framework for Contrastive Learning of Visual Representations\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.05709)\n    [[code]](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fsimclr)\n    - Ting Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey Hinton. *ICML 2020*\n   \n - How Useful is Self-Supervised Pretraining for Visual Tasks?\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2003.14323)\n    [[code]](https:\u002F\u002Fgithub.com\u002Fprinceton-vl\u002Fselfstudy-render)\n    - Alejandro Newell, Jia Deng. *CVPR 2020*\n\n - Momentum Contrast for Unsupervised Visual Representation Learning\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1911.05722.pdf)\n    [[code](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fmoco)]\n    - Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, Ross Girshick. *CVPR 2020*\n\n- ClusterFit: Improving Generalization of Visual Representations\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1912.03330)\n   - Xueting Yan*, Ishan Misra*, Abhinav Gupta, Deepti Ghadiyaram**, Dhruv Mahajan**. *CVPR 2020*\n\n- Self-Supervised Learning of Pretext-Invariant Representations\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1912.01991)\n   - Ishan Misra, Laurens van der Maaten. *CVPR 2020*\n   \n- Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.07733)\n    [[unofficial-code]](https:\u002F\u002Fgithub.com\u002Flucidrains\u002Fbyol-pytorch)\n    - Jean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec, Pierre H. Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhaohan Daniel Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, Rémi Munos, Michal Valko. *NeurIPS 2020, Oral*\n    \n - Contrastive learning of global and local features for medical image segmentation with limited annotations\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.10511.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002Fkrishnabits001\u002Fdomain_specific_cl)\n    - Krishna Chaitanya, Ertunc Erdil, Neerav Karani, Ender Konukoglu. *NeurIPS 2020, Oral*\n\n - Unsupervised Representation Learning by InvariancePropagation\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2010.11694.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002FWangFeng18\u002FInvariancePropagation)\n    - Feng Wang, Huaping Liu, Di Guo, Fuchun Sun. *NeurIPS 2020, Spotlight*\n\n - Big Self-Supervised Models are Strong Semi-Supervised Learners\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.10029)\n    [[code]](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fsimclr)\n    - Ting Chen, Simon Kornblith, Kevin Swersky, Mohammad Norouzi, Geoffrey Hinton. *NeurIPS 2020*\n    \n - Self-Supervised Prototypical Transfer Learning for Few-Shot Classification\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.11325.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002Findy-lab\u002FProtoTransfer)\n    - Carlos Medina, Arnout Devos, Matthias Grossglauser\n\n - SCAN: Learning to Classify Images without Labels\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.12320)\n    [[code]](https:\u002F\u002Fgithub.com\u002Fwvangansbeke\u002FUnsupervised-Classification)\n    - Wouter Van Gansbeke, Simon Vandenhende, Stamatios Georgoulis, Marc Proesmans, Luc Van Gool. *ECCV 2020*\n  \n - Unsupervised Learning of Visual Features by Contrasting Cluster Assignments\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.09882)\n    [[code]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fswav)\n    - Mathilde Caron, Ishan Misra, Julien Mairal, Priya Goyal, Piotr Bojanowski, Armand Joulin. *NeurIPS 2020*\n    \n - Self-Supervised Relational Reasoning for Representation Learning\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.05849.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002Fmpatacchiola\u002Fself-supervised-relational-reasoning)\n    - Massimiliano Patacchiola, Amos Storkey. *NeurIPS 2020, Spotlight*\n\n - Exploring Simple Siamese Representation Learning\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2011.10566)\n    [[unofficial-code]](https:\u002F\u002Fgithub.com\u002FPatrickHua\u002FSimSiam)\n    - Xinlei Chen, Kaiming He\n\n - Online Bag-of-Visual-Words Generation for Unsupervised Representation Learning\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2012.11552)\n    [[code]](https:\u002F\u002Fgithub.com\u002Fvaleoai\u002Fobow)\n    - Spyros Gidaris, Andrei Bursuc, Gilles Puy, Nikos Komodakis, Matthieu Cord, Patrick Pérez\n\n - Rethinking the Value of Labels for Improving Class-Imbalanced Learning\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.07529)\n    [[code]](https:\u002F\u002Fgithub.com\u002FYyzHarry\u002Fimbalanced-semi-self)\n    - Yuzhe Yang, Zhi Xu. *NeurIPS 2020*\n\n- Demystifying contrastive self-supervised learning: Invariances, augmentations and dataset biases\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2007.13916.pdf)\n    - Senthil Purushwalkam, Abhinav Gupta. *NeurIPS 2020*\n    \n- Mitigating embedding and class assignment mismatch in unsupervised image classification\n    [[pdf]](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-58586-0_45)\n    [[code]](https:\u002F\u002Fgithub.com\u002FSungwon-Han\u002FTwoStageUC)\n    - Sungwon Han, Sungwon Park, Sungkyu Park, Sundong Kim, Meeyoung Cha. *ECCV 2020*\n\n#### 2021\n - Self-Supervised Learning Across Domains\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.12368)\n    - Silvia Bucci, Antonio D'Innocente, Yujun Liao, Fabio Maria Carlucci, Barbara Caputo, Tatiana Tommasi. *T-PAMI 2021*\n\n - Barlow twins: Self-supervised learning via redundancy reduction \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2103.03230)\n  [[code]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fbarlowtwins) \n    - Zbontar, J., Jing, L., Misra, I., LeCun, Y., & Deny, S.\n\n - Contrastive Semi-Supervised Learning for 2D Medical Image Segmentation\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.06801)\n   - Prashant Pandey, Ajey Pai, Nisarg Bhatt, Prasenjit Das, Govind Makharia, Prathosh AP, Mausam. *MICCAI 2021*\n   \n - Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2011.10043)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fzdaxie\u002FPixPro)\n   - Zhenda Xie, Yutong Lin, Zheng Zhang, Yue Cao, Stephen Lin, and Han Hu. *CVPR 2021*\n\n - How Well Do Self-Supervised Models Transfer?\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.13377)\n   [[code]](https:\u002F\u002Fgithub.com\u002Flinusericsson\u002Fssl-transfer)\n   - Linus Ericsson, Henry Gouk, Timothy M. Hospedales. *CVPR 2021*\n\n- Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting.  \n  [[code]](https:\u002F\u002Fgithub.com\u002FAyanKumarBhunia\u002FSelf-Supervised-Learning-for-Sketch)\n  - Ayan Kumar Bhunia, Pinaki nath Chowdhury, Yongxin Yang, Timothy Hospedales, Tao Xiang, Yi-Zhe Song. *CVPR 2021*\n\n - SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.07724)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fcjrd\u002Fselfaugment)\n   - Colorado Reed, Sean Metzger, Aravind Srinivas, Trevor Darrell, Kurt Keutzer. *CVPR 2021*\n \n - Jigsaw Clustering for Unsupervised Visual Representation Learning\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.00323)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fdvlab-research\u002FJigsawClustering)\n   - Pengguang Chen, Shu Liu, Jiaya Jia. *CVPR 2021*\n   \n - Improving Unsupervised Image Clustering With Robust Learning\n   [[pdf]](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2021\u002Fpapers\u002FPark_Improving_Unsupervised_Image_Clustering_With_Robust_Learning_CVPR_2021_paper.pdf)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fdeu30303\u002FRUC)\n   - Sungwon Park, Sungwon Han, Sundong Kim, Danu Kim, Sungkyu Park, Seunghoon Hong, Meeyoung Cha. *CVPR 2021*\n\n - Improving Contrastive Learning by Visualizing Feature Transformation\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2108.02982)\n   [[code]](https:\u002F\u002Fgithub.com\u002FDTennant\u002FCL-Visualizing-Feature-Transformation)\n   - Rui Zhu*, Bingchen Zhao*, Jingen Liu, Zhenglong Sun, Chang Wen Chen. *ICCV 2021 Oral*\n\n#### 2022\n - Tailoring Self-Supervision for Supervised Learning\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2207.10023)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fwjun0830\u002FLocalizable-Rotation)\n   - WonJun Moon, Ji-Hwan Kim, Jae-Pil Heo. *ECCV 2022*\n   \n - FedX: Unsupervised Federated Learning with Cross Knowledge Distillation\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2207.09158)\n   [[code]](https:\u002F\u002Fgithub.com\u002FSungwon-Han\u002FFEDX)\n   - Sungwon Han, Sungwon Park, Fangzhao Wu, Sundong Kim, Chuhan Wu, Xing Xie, Meeyoung Cha. *ECCV 2022*\n  \n - Masked Siamese Networks for Label-Efficient Learning\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.07141)\n   [[code]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fmsn)\n   - Mahmoud Assran, Mathilde Caron, Ishan Misra, Piotr Bojanowski, Florian Bordes, Pascal Vincent, Armand Joulin, Michael Rabbat, Nicolas Ballas.\n\n - TriBYOL: Triplet BYOL for Self-Supervised Representation Learning\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.03012)\n   - Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama. *ICASSP 2022*\n\n - Self-Knowledge Distillation based Self-Supervised Learning for Covid-19 Detection from Chest X-Ray Images\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.03009)\n   - Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama. *ICASSP 2022*\n \n - Adaptive Soft Contrastive Learning\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2207.11163)\n   [[code]](https:\u002F\u002Fgithub.com\u002FMrChenFeng\u002FASCL_ICPR2022)\n   - Chen Feng, Ioannis Patras. *ICPR 2022*\n   \n  - Self-Supervised Visual Representation Learning with Semantic Grouping \n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.15288) \n    [[code]](https:\u002F\u002Fgithub.com\u002FCVMI-Lab\u002FSlotCon)\n    - Xin Wen, Bingchen Zhao, Anlin Zheng, Xiangyu Zhang, and Xiaojuan Qi. *NeurIPS 2022*\n   \n - VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2105.04906)\n   - Adrien Bardes, Jean Ponce, Yann LeCun. *ICLR 2022*  \n\n#### 2023\n - Inter-Instance Similarity Modeling for Contrastive Learning\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.12243) \n   [[code]](https:\u002F\u002Fgithub.com\u002Fvisresearch\u002Fpatchmix)\n   - Chengchao Shen, Dawei Liu, Hao Tang, Zhe Qu, Jianxin Wang. \n - Asymmetric Patch Sampling for Contrastive Learning\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.02854)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fvisresearch\u002Faps)\n   - Chengchao Shen, Jianzhong Chen, Shu Wang, Hulin Kuang, Jin Liu, Jianxin Wang.\n\n#### 2024\n - Towards evolution of Deep Neural Networks through contrastive Self-Supervised learning\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2406.14525) \n   [[code]](https:\u002F\u002Fgithub.com\u002Fcdvetal\u002Fevodenss)\n   - Adriano Vinhas, João Correia, Penousal Machado. *CEC 2024*\n\n### Video Representation Learning\n\n- Unsupervised Learning of Video Representations using LSTMs.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1502.04681.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Femansim\u002Funsupervised-videos)\n  - Srivastava, Nitish and Mansimov, Elman and Salakhudinov, Ruslan. *ICML 2015*\n\n- Shuffle and Learn: Unsupervised Learning using Temporal Order Verification. \n  [[pdf]](http:\u002F\u002Farxiv.org\u002Fabs\u002F1603.08561) \n  [[code]](https:\u002F\u002Fgithub.com\u002Fimisra\u002Fshuffle-tuple)\n  - Ishan Misra, C. Lawrence Zitnick and Martial Hebert. *ECCV 2016*\n  \n- LSTM Self-Supervision for Detailed Behavior Analysis\n  [[pdf]](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2017\u002Fpapers\u002FBrattoli_LSTM_Self-Supervision_for_CVPR_2017_paper.pdf)\n  - Biagio Brattoli*, Uta Büchler*, Anna-Sophia Wahl, Martin E. Schwab, and Björn Ommer. *CVPR 2017*\n  \n- Self-Supervised Video Representation Learning With Odd-One-Out Networks. \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1611.06646) \n  - Basura Fernando and Hakan Bilen and Efstratios Gavves and Stephen Gould. *CVPR 2017*\n\n- Unsupervised Learning of Long-Term Motion Dynamics for Videos. \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1701.01821.pdf)\n  - Luo, Zelun and Peng, Boya and Huang, De-An and Alahi, Alexandre and Fei-Fei, Li. *CVPR 2017*\n\n- Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation Learning.\n  [[pdf]](http:\u002F\u002Fai.ucsd.edu\u002F~haosu\u002Fpapers\u002Fcvpr18_geometry_predictive_learning.pdf) \n  - Chuang Gan and Boqing Gong and Kun Liu and Hao Su and Leonidas J. Guibas. *CVPR 2018*\n  \n- Improving Spatiotemporal Self-Supervision by Deep Reinforcement Learning.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1807.11293)\n  - Biagio Brattoli*, Uta Büchler*, and Björn Ommer. *ECCV 2018*\n\n- Self-supervised learning of a facial attribute embedding from video.\n  [[pdf]](http:\u002F\u002Fwww.robots.ox.ac.uk\u002F~vgg\u002Fpublications\u002F2018\u002FWiles18a\u002Fwiles18a.pdf)\n  - Wiles, O.*, Koepke, A.S.*, Zisserman, A. *BMVC 2018*\n\n- Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles. \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1811.09795.pdf)\n  - Kim, Dahun and Cho, Donghyeon and Yoo, Donggeun and Kweon, In So. *AAAI 2019*\n\n- Self-Supervised Spatio-Temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1904.03597)\n  - Jiangliu Wang; Jianbo Jiao; Linchao Bao; Shengfeng He; Yunhui Liu; Wei Liu. CVPR 2019\n\n- DynamoNet: Dynamic Action and Motion Network.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1904.11407.pdf)\n  - Ali Diba; Vivek Sharma, Luc Van Gool, Rainer Stiefelhagen. *ICCV 2019*\n\n- Learning Correspondence from the Cycle-consistency of Time.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1903.07593) \n  [[code]](https:\u002F\u002Fgithub.com\u002Fxiaolonw\u002FTimeCycle)\n  - Xiaolong Wang*, Allan Jabri* and Alexei A. Efros. *CVPR 2019*\n\n- Joint-task Self-supervised Learning for Temporal Correspondence.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.11895) \n  [[code]](https:\u002F\u002Fgithub.com\u002FLiusifei\u002FUVC)\n  - Xueting Li*, Sifei Liu*, Shalini De Mello, Xiaolong Wang, Jan Kautz, and Ming-Hsuan Yang. *NIPS 2019*\n\n- Self-Supervised Video Representation Learning Using Inter-Intra Contrstive Framework\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2008.02531.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002FBestJuly\u002FIIC)\n  - Li Tao, Xueting Wang*, Toshihiko Yamasaki. *ACMMM 2020*\n  \n- Video Playback Rate Perception for Self-Supervised Spatio-Temporal Representation Learning\n  [[pdf]](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_CVPR_2020\u002Fpapers\u002FYao_Video_Playback_Rate_Perception_for_Self-Supervised_Spatio-Temporal_Representation_Learning_CVPR_2020_paper.pdf)\n  [[Code]](https:\u002F\u002Fgithub.com\u002Fyuanyao366\u002FPRP)\n  - Yuan Yao*, Chang Liu*, Dezhao Luo, Yu Zhou, Qixiang Ye. *CVPR 2020*\n  \n- Self-Supervised Video Representation Learning by Pace Prediction\n  [[pdf]](http:\u002F\u002Fwww.robots.ox.ac.uk\u002F~vgg\u002Fpublications\u002F2020\u002FWang20\u002Fwang20.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Flaura-wang\u002Fvideo-pace)\n  - Jiangliu Wang, Jianbo Jiao, Yun-Hui Liu. *ECCV 2020*\n  \n- Video Representation Learning by Recognizing Temporal Transformations\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2007.10730.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fsjenni\u002Ftemporal-ssl)\n  - Simon Jenni, Givi Meishvili, Paolo Favaro. *ECCV 2020*\n  \n- Self-supervised Co-training for Video Representation Learning\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2010.09709)\n  [[code]](https:\u002F\u002Fgithub.com\u002FTengdaHan\u002FCoCLR)\n  - Tengda Han, Weidi Xie, and Andrew Zisserman. *NeurIPS 2020*\n\n- Cycle-Contrast for Self-Supervised Video Representation Learning\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2010.14810)\n  - Quan Kong, Wenpeng Wei, Ziwei Deng, Tomoaki Yoshinaga, and Tomokazu Murakami. *NeurIPS 2020*\n\n- Video Representation Learning with Visual Tempo Consistency\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.15489)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fdecisionforce\u002FVTHCL)\n  - Ceyuan Yang, Yinghao Xu, Bo Dai, and Bolei Zhou\n\n- Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2008.13426)\n  - Jiangliu Wang, Jianbo Jiao, Linchao Bao, Shengfeng He, Wei Liu, and Yun-hui Liu\n\n- Spatiotemporal Contrastive Video Representation Learning\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2008.03800)\n  - Rui Qian, Tianjian Meng, Boqing Gong, Ming-Hsuan Yang, Huisheng Wang, Serge Belongie, and Yin Cui\n\n- Self-Supervised Video Representation Using Pretext-Contrastive Learning\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2010.15464)\n  - Li Tao, Xueting Wang, and Toshihiko Yamasaki\n\n- Unsupervised Video Representation Learning by Bidirectional Feature Prediction\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2011.06037)\n  - Nadine Behrmann, Juergen Gall, and Mehdi Noroozi\n\n- RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2011.07949)\n  [[code]](https:\u002F\u002Fgithub.com\u002FPeihaoChen\u002FRSPNet)\n  - Peihao Chen, Deng Huang, Dongliang He, Xiang Long, Runhao Zeng, Shilei Wen, Mingkui Tan, and Chuang Gan. *AAAI 2021*\n\n- Hierarchically Decoupled Spatial-Temporal Contrast for Self-supervised Video Representation Learning\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2011.11261)\n  - Zehua Zhang and David Crandall\n\n- Can Temporal Information Help with Contrastive Self-Supervised Learning?\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2011.13046)\n  - Yutong Bai, Haoqi Fan, Ishan Misra, Ganesh Venkatesh, Yongyi Lu, Yuyin Zhou, Qihang Yu, Vikas Chandra, and Alan Yuille\n\n- Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2009.05757)\n  [[code]](https:\u002F\u002Fgithub.com\u002FFingerRec\u002FDSM-decoupling-scene-motion)\n  - Jinpeng Wang, Yuting Gao, Ke Li, Jianguo Hu, Xinyang Jiang, Xiaowei Guo, Rongrong Ji, and Xing Sun. *AAAI 2021*\n\n- Space-Time Correspondence as a Contrastive Random Walk\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.14613)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fajabri\u002Fvideowalk\u002F)\n  [[project]](http:\u002F\u002Fajabri.github.io\u002Fvideowalk)\n  - Allan Jabri, Andrew Owens, Alexei A. Efros. *NeurIPS 2020 Oral*\n  \n \n#### Benchmark code for video self-supervised learning\n- How Severe is Benchmark-Sensitivity in Video Self-Supervised Learning?\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.14221) \n  [[code]](https:\u002F\u002Fgithub.com\u002Ffmthoker\u002FSEVERE-BENCHMARK)\n  - Thoker, Fida Mohammad and Doughty, Hazel and Bagad, Piyush and Snoek, Cees . *ECCV 2022*\n\n\n### 3D Feature Learning\n- Self-Supervised Deep Learning on Point Clouds by Reconstructing Space \n  [[pdf]](http:\u002F\u002Fpapers.neurips.cc\u002Fpaper\u002F9455-self-supervised-deep-learning-on-point-clouds-by-reconstructing-space.pdf)\n  - Jonathan Sauder, and Bjarne Sievers *NeurIPS 2019*\n\n- Self-Supervised Learning of Point Clouds via Orientation Estimation \n  [[pdf]](http:\u002F\u002Fwww.vovakim.com\u002Fpapers\u002F20_3DV_RotationSupervision.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002FOmidPoursaeed\u002FSelf_supervised_Learning_Point_Clouds)\n  -  Omid Poursaeed, Tianxing Jiang, Han Qiao, Nayun Xu, and Vladimir G. Kim,*3DV 2020* \n\n- Self-Supervised Learning on 3D Point Clouds by Learning Discrete Generative Models\n  [[pdf]](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2021\u002Fpapers\u002FEckart_Self-Supervised_Learning_on_3D_Point_Clouds_by_Learning_Discrete_Generative_CVPR_2021_paper.pdf) \n  - Benjamin Eckart, Wentao Yuan,  Chao Liu,  and Jan Kautz *CVPR 2021*\n\n- PointContrast: Unsupervised Pre-training for 3D Point Cloud\n  [[pdf]](https:\u002F\u002Fwww.ecva.net\u002Fpapers\u002Feccv_2020\u002Fpapers_ECCV\u002Fpapers\u002F123480579.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002FPointContrast)\n  - Saining Xie, Jiatao Gu, Demi Guo, Charles R. Qi, Leonidas Guibas, and Or Litany *ECCV 2020*\n\n- Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2110.08188)\n  - Li Jiang, Shaoshuai Shi, Zhuotao Tian, Xin Lai, Shu Liu, Chi-Wing Fu, and Jiaya Jia *ICCV 2021*\n \n- Ponder: Point Cloud Pre-training via Neural Rendering\n  [[pdf]](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FICCV2023\u002Fhtml\u002FHuang_Ponder_Point_Cloud_Pre-training_via_Neural_Rendering_ICCV_2023_paper.html)\n  - Di Huang, Sida Peng, Tong He, Honghui Yang, Xiaowei Zhou and Wanli Ouyang *ICCV 2023*\n\n- PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.08586)\n  [[code]](https:\u002F\u002Fgithub.com\u002FOpenGVLab\u002FPonderV2)\n  - Haoyi Zhu, Honghui Yang, Xiaoyang Wu, Di Huang, Tong He, Hengshuang Zhao, Chunhua Shen, Yu Qiao and Wanli Ouyang *Arxiv 2023*\n\n- UniPAD: A Universal Pre-training Paradigm for Autonomous Driving\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.08586)\n  [[code]]([https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.08370](https:\u002F\u002Fgithub.com\u002FNightmare-n\u002FUniPAD))\n  - Honghui Yang, Sha Zhang, Di Huang, Xiaoyang Wu, Haoyi Zhu, Tong He, Shixiang Tang, Hengshuang Zhao, Qibo Qiu, Binbin Lin, Xiaofei He, Wanli Ouyang *Arxiv 2023*\n\n### Geometry\n- Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1603.04992.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002FRavi-Garg\u002FUnsupervised_Depth_Estimation)\n  -  Ravi Garg, Vijay Kumar BG, Gustavo Carneiro, Ian Reid. *ECCV 2016*\n\n-   Self-supervised Learning of Motion Capture.\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1712.01337.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002Fhtung0101\u002F3d_smpl)\n    [[web]](https:\u002F\u002Fsites.google.com\u002Fview\u002Fselfsupervisedlearningofmotion\u002F)\n    -   Tung, Hsiao-Yu and Tung, Hsiao-Wei and Yumer, Ersin and Fragkiadaki, Katerina. *NIPS 2017*\n\n- Unsupervised learning of object frames by dense equivariant image labelling.\n  [[pdf]](http:\u002F\u002Fpapers.neurips.cc\u002Fpaper\u002F6686-unsupervised-learning-of-object-frames-by-dense-equivariant-image-labelling.pdf)\n  - James Thewlis, Hakan Bilen, Andrea Vedaldi. *NeurIPS 2017*\n\n-   Unsupervised Learning of Depth and Ego-Motion from Video. \n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1704.07813.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002Ftinghuiz\u002FSfMLearner)\n    [[web]](https:\u002F\u002Fpeople.eecs.berkeley.edu\u002F~tinghuiz\u002Fprojects\u002FSfMLearner\u002F)\n    -   Zhou, Tinghui and Brown, Matthew and Snavely, Noah and Lowe, David G. *CVPR 2017*\n    \n- Active Stereo Net: End-to-End Self-Supervised Learning for Active Stereo Systems.\n  [[project]](http:\u002F\u002Fasn.cs.princeton.edu\u002F)\n  - Yinda Zhang*, Sean Fanello, Sameh Khamis, Christoph Rhemann, Julien Valentin, Adarsh Kowdle, Vladimir Tankovich, Shahram Izadi, Thomas Funkhouser. *ECCV 2018*\n\n- Self-Supervised Relative Depth Learning for Urban Scene Understanding.\n  [[pdf]](https:\u002F\u002Fpeople.cs.umass.edu\u002F~hzjiang\u002Ffiles\u002Fssr_depth.pdf)\n  [[project]](https:\u002F\u002Fpeople.cs.umass.edu\u002F~hzjiang\u002Fprojects\u002Fssr_depth\u002F)\n  - Huaizu Jiang*, Erik Learned-Miller, Gustav Larsson, Michael Maire, Greg Shakhnarovich. *ECCV 2018*\n\n- Geometry-Aware Learning of Maps for Camera Localization.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1712.03342)\n  [[code]](https:\u002F\u002Fgithub.com\u002FNVlabs\u002Fgeomapnet)\n  - Samarth Brahmbhatt, Jinwei Gu, Kihwan Kim, James Hays, and Jan Kautz. CVPR 2018\n\n- Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspection.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1804.01552)\n  [[web]](http:\u002F\u002Fwww.robots.ox.ac.uk\u002F~vgg\u002Fresearch\u002Fprobabilistic_introspection\u002F)\n  - David Novotny, Samuel Albanie, Diane Larlus, Andrea Vedaldi. CVPR 2018\n\n- Self-Supervised Learning of 3D Human Pose Using Multi-View Geometry.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1903.02330)\n  - Muhammed Kocabas; Salih Karagoz; Emre Akbas. CVPR 2019\n\n- SelFlow: Self-Supervised Learning of Optical Flow.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1904.09117)\n  - Jiangliu Wang; Jianbo Jiao; Linchao Bao; Shengfeng He; Yunhui Liu; Wei Liu. CVPR 2019\n\n- Unsupervised Learning of Landmarks by Descriptor Vector Exchange.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.06427)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fjamt9000\u002FDVE)\n  [[web]](http:\u002F\u002Fwww.robots.ox.ac.uk\u002F~vgg\u002Fresearch\u002FDVE\u002F)\n  - James Thewlis, Samuel Albanie, Hakan Bilen, Andrea Vedaldi. ICCV 2019\n \n\n### Audio\n- Audio-Visual Scene Analysis with Self-Supervised Multisensory Features.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1804.03641.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fandrewowens\u002Fmultisensory)\n  - Andrew Owens, Alexei A. Efros. *ECCV 2018*\n  \n- Objects that Sound.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1712.06651.pdf)\n  -  R. Arandjelović, A. Zisserman. *ECCV 2018* \n  \n- Learning to Separate Object Sounds by Watching Unlabeled Video.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1804.01665)\n  [[project]](http:\u002F\u002Fvision.cs.utexas.edu\u002Fprojects\u002Fseparating_object_sounds\u002F)\n  - Ruohan Gao, Rogerio Feris, Kristen Grauman.  *ECCV 2018*\n  \n- The Sound of Pixels.\n  [[pdf]]( https:\u002F\u002Farxiv.org\u002Fpdf\u002F1804.03160.pdf )\n  [[project]](https:\u002F\u002Fgithub.com\u002Fhangzhaomit\u002FSound-of-Pixels)\n  - Zhao, Hang and Gan, Chuang and Rouditchenko, Andrew and Vondrick, Carl and McDermott, Josh and Torralba, Antonio. *ECCV 2018*\n\n- Learnable PINs: Cross-Modal Embeddings for Person Identity.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1805.00833)\n  [[web]](http:\u002F\u002Fwww.robots.ox.ac.uk\u002F~vgg\u002Fresearch\u002FLearnablePins\u002F)\n  - Arsha Nagrani, Samuel Albanie, Andrew Zisserman. ECCV 2018\n\n\n- Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization. \n  [[pdf]](http:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F8002-cooperative-learning-of-audio-and-video-models-from-self-supervised-synchronization.pdf)\n  - Bruno Korbar,Dartmouth College, Du Tran, Lorenzo Torresani. *NIPS 2018*\n  \n- Self-Supervised Generation of Spatial Audio for 360° Video.\n  [[pdf]](http:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F7319-self-supervised-generation-of-spatial-audio-for-360-video.pdf)\n  - Pedro Morgado, Nuno Nvasconcelos, Timothy Langlois, Oliver Wang. *NIPS 2018*\n  \n- TriCycle: Audio Representation Learning from Sensor Network Data Using Self-Supervision\n  [[pdf]](http:\u002F\u002Fwww.justinsalamon.com\u002Fuploads\u002F4\u002F3\u002F9\u002F4\u002F4394963\u002Fcartwright_tricycle_waspaa2019.pdf)\n  - Mark Cartwright, Jason Cramer, Justin Salamon, Juan Pablo Bello. *WASPAA 2019*\n\n- Self-supervised audio-visual co-segmentation\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1904.09013.pdf)\n  - Andrew Rouditchenko, Hang Zhao, Chuang Gan, Josh McDermott, and Antonio Torralba. *ICASSP 2019*\n  \n- Does Visual Self-Supervision Improve Learning of Speech Representations?\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2005.01400.pdf)\n   - Abhinav Shukla, Stavros Petridis, Maja Pantic\n- There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge \n  [[pdf]](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2021\u002Fpapers\u002FValverde_There_Is_More_Than_Meets_the_Eye_Self-Supervised_Multi-Object_Detection_CVPR_2021_paper.pdf) \n  [[code]](https:\u002F\u002Fgithub.com\u002Frobot-learning-freiburg\u002FMM-DistillNet)\n\t- Francisco Rivera Valverde, Juana Valeria Hurtado, and Abhinav Valada. *CVPR 2021*\n\n- BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation.\n [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2103.06695.pdf) \n [[code]](https:\u002F\u002Fgithub.com\u002Fnttcslab\u002Fbyol-a)\n  - Daisuke Niizumi; Daiki Takeuchi; Yasunori Ohishi *IJCNN 2021*\n\n- Learning State-Aware Visual Representations from Audible Interactions\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.13583)\n  [[code]](https:\u002F\u002Fgithub.com\u002FHimangiM\u002FRepLAI)\n  - Himangi Mittal, Pedro Morgado, Unnat Jain, Abhinav Gupta. *NeurIPS 2022*\n\n### Others\n- Self-supervised Learning for Human Activity Recognition Using 700,000 Person-days of Wearable Data \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.02909) \n  [[code]](https:\u002F\u002Fgithub.com\u002FOxWearables\u002Fssl-wearables)\n  - Hang Yuan*, Shing Chan*, Andrew P. Creagh, Catherine Tong, David A. Clifton, Aiden Doherty\n  \n- Self-learning Scene-specific Pedestrian Detectors using a Progressive Latent Model.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1611.07544)\n  - Qixiang Ye, Tianliang Zhang, Qiang Qiu, Baochang Zhang, Jie Chen, Guillermo Sapiro. *CVPR 2017*\n  \n- Free Supervision from Video Games.\n  [[pdf]](http:\u002F\u002Fwww.philkr.net\u002Fpapers\u002F2018-06-01-cvpr\u002F2018-06-01-cvpr.pdf)\n  [[project+code]](http:\u002F\u002Fwww.philkr.net\u002Ffsv\u002F)\n  - Philipp Krähenbühl. *CVPR 2018*\n  \n- Fighting Fake News: Image Splice Detection via Learned Self-Consistency\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1805.04096.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fminyoungg\u002Fselfconsistency)\n  - Minyoung Huh*, Andrew Liu*, Andrew Owens, Alexei A. Efros. *ECCV 2018*\n  \n- Self-supervised Tracking by Colorization (Tracking Emerges by Colorizing Videos).\n  [[pdf]](https:\u002F\u002Fwww.cs.columbia.edu\u002F~vondrick\u002F\u002Fvideocolor.pdf)\n  - Carl Vondrick*, Abhinav Shrivastava, Alireza Fathi, Sergio Guadarrama, Kevin Murphy. *ECCV 2018*\n  \n- High-Fidelity Image Generation With Fewer Labels.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.02271.pdf)\n  - Mario Lucic*, Michael Tschannen*, Marvin Ritter*, Xiaohua Zhai, Olivier Bachem, Sylvain Gelly.\n  \n- Self-supervised Fitting of Articulated Meshes to Point Clouds.\n  - Chun-Liang Li, Tomas Simon, Jason Saragih, Barnabás Póczos and Yaser Sheikh. *CVPR 2019*\n  \n- Just Go with the Flow: Self-Supervised Scene Flow Estimation\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1912.00497.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002FHimangiM\u002FJust-Go-with-the-Flow-Self-Supervised-Scene-Flow-Estimation)\n  - Himangi Mittal, Brian Okorn, David Held. *CVPR 2020*\n  \n- SCOPS: Self-Supervised Co-Part Segmentation. \n  - Wei-Chih Hung, Varun Jampani, Sifei Liu, Pavlo Molchanov, Ming-Hsuan Yang, and Jan Kautz. *CVPR 2019*\n  \n- Self-Supervised Adaptation of High-Fidelity Face Models for Monocular Performance Tracking.\n  - Jae Shin Yoon; Takaaki Shiratori; Shoou-I Yu; Hyun Soo Park. *CVPR 2019*\n  \n- Multi-Task Self-Supervised Object Detection via Recycling of Bounding Box Annotations.\n [[pdf]](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_CVPR_2019\u002Fpapers\u002FLee_Multi-Task_Self-Supervised_Object_Detection_via_Recycling_of_Bounding_Box_Annotations_CVPR_2019_paper.pdf) \n [[code]](https:\u002F\u002Fgithub.com\u002FwonheeML\u002Fmtl-ssl)\n  - Wonhee Lee; Joonil Na; Gunhee Kim. *CVPR 2019*\n  \n- Self-Supervised Convolutional Subspace Clustering Network.\n  - Junjian Zhang; Chun-Guang Li; Chong You; Xianbiao Qi; Honggang Zhang; Jun Guo; Zhouchen Lin. *CVPR 2019*\n  \n- Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation.\n  - Xin Wang; Qiuyuan Huang; Asli Celikyilmaz; Jianfeng Gao; Dinghan Shen; Yuan-Fang Wang; William Yang Wang; Lei Zhang. *CVPR 2019*\n  \n- Unsupervised 3D Pose Estimation With Geometric Self-Supervision.\n  - Ching-Hang Chen; Ambrish Tyagi; Amit Agrawal; Dylan Drover; Rohith MV; Stefan Stojanov; James M. Rehg. *CVPR 2019*\n  \n- Learning to Generate Grounded Image Captions without Localization Supervision. [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1906.00283.pdf)\n  - Chih-Yao Ma; Yannis Kalantidis; Ghassan AlRegib; Peter Vajda; Marcus Rohrbach; Zsolt Kira.\n- VideoBERT: A Joint Model for Video and Language Representation Learning [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1904.01766.pdf)\n  - Chen Sun, Austin Myers, Carl Vondrick, Kevin Murphy, Cordelia Schmid. *ICCV 2019*\n  \n- Countering Noisy Labels By Learning From Auxiliary Clean Labels [[pdf]]( https:\u002F\u002Farxiv.org\u002Fpdf\u002F1905.13305.pdf )\n  - Tsung Wei Tsai, Chongxuan Li, Jun Zhu\n\n- Self-Supervised Point Cloud Completion via Inpainting\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2111.10701)\n  - Himangi Mittal, Brian Okorn, Arpit Jangid, David Held. *BMVC 2021*\n  \n- ColloSSL: Collaborative Self-Supervised Learning for Human Activity Recognition\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2202.00758.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fakhilmathurs\u002Fcollossl)\n  - Yash Jain, Ian Tang, Chulhong Min, Fahim Kawsar, Akhil Mathur. *UbiComp 2022*\n  \n## Machine Learning\n-   Self-taught Learning: Transfer Learning from Unlabeled Data.\n    [[pdf]](https:\u002F\u002Fai.stanford.edu\u002F~hllee\u002Ficml07-selftaughtlearning.pdf)\n    -   Raina, Rajat and Battle, Alexis and Lee, Honglak and Packer,\n        Benjamin and Ng, Andrew Y. *ICML 2007*\n\n-   Representation Learning: A Review and New Perspectives.\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1206.5538.pdf)\n    -   Bengio, Yoshua and Courville, Aaron and Vincent, Pascal. *TPAMI 2013*.\n\n### Reinforcement Learning\n- Curiosity-driven Exploration by Self-supervised Prediction. \n  [[pdf]](http:\u002F\u002Fpathak22.github.io\u002Fnoreward-rl\u002Fresources\u002Ficml17.pdf) \n  [[code]](https:\u002F\u002Fpathak22.github.io\u002Fnoreward-rl\u002Findex.html#sourceCode)\n  - Deepak Pathak, Pulkit Agrawal, Alexei A. Efros, and Trevor Darrell. *ICML 2017*\n\n- Large-Scale Study of Curiosity-Driven Learning.\n  [[pdf]](https:\u002F\u002Fpathak22.github.io\u002Flarge-scale-curiosity\u002Fresources\u002FlargeScaleCuriosity2018.pdf) \n  - Yuri Burda*, Harri Edwards*, Deepak Pathak*, Amos Storkey, Trevor Darrell and Alexei A. Efros\n\n- Playing hard exploration games by watching YouTube.\n  [[pdf]](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F7557-playing-hard-exploration-games-by-watching-youtube.pdf) \n  - Yusuf Aytar, Tobias Pfaff, David Budden, Tom Le Paine, Ziyu Wang, Nando de Freitas. *NIPS 2018*\n  \n- Unsupervised State Representation Learning in Atari.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1906.08226.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fmila-iqia\u002Fatari-representation-learning)\n  - Ankesh Anand, Evan Racah, Sherjil Ozair, Yoshua Bengio, Marc-Alexandre Côté, R Devon Hjelm. *NeurIPS 2019*\n\n- Visual Reinforcement Learning with Self-Supervised 3D Representations.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2210.07241.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002FYanjieZe\u002Frl3d)\n  - Yanjie Ze*, Nicklas Hansen*, Yinbo Chen, Mohit Jain, Xiaolong Wang. *Preprint 2022*\n\n### Recommendation Systems\n- Self-supervised Learning for Deep Models in Recommendations.\n  [[pdf](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2007.12865.pdf)]\n  - Tiansheng Yao, Xinyang Yi, Derek Zhiyuan Cheng, Felix Yu, Aditya Menon, Lichan Hong, Ed H. Chi, Steve Tjoa, Jieqi (Jay)Kang, Evan Ettinger *Preprint 2020*\n\n\n## Robotics\n\n### 2006\n- Improving Robot Navigation Through Self-Supervised Online Learning\n  [[pdf]](http:\u002F\u002Fwww.roboticsproceedings.org\u002Frss02\u002Fp04.pdf)\n  - Boris Sofman, Ellie Lin, J. Andrew Bagnell, Nicolas Vandapel, and Anthony Stentz\n  \n- Reverse Optical Flow for Self-Supervised Adaptive Autonomous Robot Navigation\n  [[pdf]](https:\u002F\u002Fwww.cs.ait.ac.th\u002F~mdailey\u002Fcvreadings\u002FLookingbill-ReverseOptical.pdf)\n  - A. Lookingbill, D. Lieb, J. Rogers and J. Curry\n\n### 2009\n- Learning Long-Range Vision for Autonomous Off-Road Driving\n  [[pdf]](http:\u002F\u002Fyann.lecun.com\u002Fexdb\u002Fpublis\u002Fpdf\u002Fhadsell-jfr-09.pdf)\n  - Raia Hadsell, Pierre Sermanet, Jan Ben, Ayse Erkan, Marco Scoffier, Koray Kavukcuoglu, Urs Muller, Yann LeCun\n\n### 2012\n- Self-supervised terrain classification for planetary surface exploration rovers\n  [[pdf]](https:\u002F\u002Fpdfs.semanticscholar.org\u002F66b7\u002Feef326d1db1fa2b19d5dc6b84d3d2a95b76c.pdf)\n  - Christopher A. Brooks, Karl Iagnemma \n  \n### 2014\n- Terrain Traversability Analysis Using Multi-Sensor Data Correlation by a Mobile Robot\n  [[pdf]](http:\u002F\u002Fsensor.eng.shizuoka.ac.jp\u002Fpdf\u002F2014\u002FSII.pdf)\n  - Mohammed Abdessamad Bekhti, Yuichi Kobayashi and Kazuki Matsumura\n  \n### 2015\n- Online self-supervised learning for dynamic object segmentation\n  [[pdf]](http:\u002F\u002Fciteseerx.ist.psu.edu\u002Fviewdoc\u002Fdownload?doi=10.1.1.875.5829&rep=rep1&type=pdf)\n  - Vitor Guizilini and Fabio Ramos, The International Journal of Robotics Research\n\n- Self-Supervised Online Learning of Basic Object Push Affordances\n  [[pdf]](http:\u002F\u002Fabr.ijs.si\u002Fpdf\u002F1429861734-RidgeIJARS2015.pdf)\n  - Barry Ridge, Ales Leonardis, Ales Ude, Miha Denisa, and Danijel Skocaj\n  \n- Self-supervised learning of grasp dependent tool affordances on the iCub Humanoid robot\n  [[pdf]](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=7139640)\n  - Tanis Mar, Vadim Tikhanoff, Giorgio Metta, and Lorenzo Natale\n\n### 2016\n- Persistent self-supervised learning principle: from stereo to monocular vision for obstacle avoidance\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1603.08047.pdf)\n  - Kevin van Hecke, Guido de Croon, Laurens van der Maaten, Daniel Hennes, and Dario Izzo\n\n- The Curious Robot: Learning Visual Representations via Physical Interactions. \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1604.01360v2)\n  - Lerrel Pinto and Dhiraj Gandhi and Yuanfeng Han and Yong-Lae Park and Abhinav Gupta. *ECCV 2016*\n\n-   Learning to Poke by Poking: Experiential Learning of Intuitive Physics.\n    [\\[pdf\\]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1606.07419)\n    -   Agrawal, Pulkit and Nair, Ashvin V and Abbeel, Pieter and Malik, Jitendra and Levine, Sergey. *NIPS 2016*\n\n-   Supersizing Self-supervision: Learning to Grasp from 50K Tries and\n    700 Robot Hours. [\\[pdf\\]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1509.06825.pdf)\n    -   Pinto, Lerrel and Gupta, Abhinav. *ICRA 2016*\n    \n### 2017\n-  Supervision via Competition: Robot Adversaries for Learning Tasks.\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1610.01685.pdf)\n   - Pinto, Lerrel and Davidson, James and Gupta, Abhinav. *ICRA 2017*\n\n- Multi-view Self-supervised Deep Learning for 6D Pose Estimation in the Amazon Picking Challenge.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1803.09956.pdf) \n  [[Project]](http:\u002F\u002Fapc.cs.princeton.edu\u002F)\n  - Andy Zeng, Kuan-Ting Yu, Shuran Song, Daniel Suo, Ed Walker Jr., Alberto Rodriguez, Jianxiong Xiao. *ICRA 2017* \n\n- Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1703.02018) \n  [[Project]](https:\u002F\u002Fropemanipulation.github.io\u002F)\n  - Ashvin Nair*, Dian Chen*, Pulkit Agrawal*, Phillip Isola, Pieter Abbeel, Jitendra Malik, Sergey Levine. *ICRA 2017*\n\n- Learning to Fly by Crashing\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1704.05588)\n  - Dhiraj Gandhi, Lerrel Pinto, Abhinav Gupta *IROS 2017*\n  \n- Self-supervised learning as an enabling technology for future space exploration robots: ISS experiments on monocular distance learning\n  [[pdf]](http:\u002F\u002Fwww.esa.int\u002Fgsp\u002FACT\u002Fdoc\u002FAI\u002Fpub\u002FACT-RPR-AI-2017-ACTA-SSL.pdf)\n  - K. van Hecke, G. C. de Croon, D. Hennes, T. P. Setterfield, A. Saenz- Otero, and D. Izzo\n\n- Unsupervised Perceptual Rewards for Imitation Learning.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1612.06699)\n  [[project]](https:\u002F\u002Fsermanet.github.io\u002Frewards\u002F)\n  - Sermanet, Pierre and Xu, Kelvin and Levine, Sergey. *RSS 2017*\n\n- Self-Supervised Visual Planning with Temporal Skip Connections.\n  [[pdf]](http:\u002F\u002Farxiv.org\u002Fpdf\u002F1710.05268)\n  - Frederik Ebert, Chelsea Finn, Alex X. Lee, Sergey Levine. *CoRL2017*\n\n### 2018\n- CASSL: Curriculum Accelerated Self-Supervised Learning. \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1708.01354.pdf) \n  - Adithyavairavan Murali, Lerrel Pinto, Dhiraj Gandhi, Abhinav Gupta. *ICRA 2018*\n\n- Time-Contrastive Networks: Self-Supervised Learning from Video. \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1609.09475.pdf) \n  [[Project]](https:\u002F\u002Fsermanet.github.io\u002Fimitate\u002F)\n  - Pierre Sermanet and Corey Lynch and Yevgen Chebotar and Jasmine Hsu and Eric Jang and Stefan Schaal and Sergey Levine. *ICRA 2018*\n\n- Self-Supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation. \n  [[pdf]](http:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.10489) \n  - Gregory Kahn, Adam Villaflor, Bosen Ding, Pieter Abbeel, Sergey Levine. *ICRA 2018*\n\n- Learning Actionable Representations from Visual Observations. \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1609.09475.pdf) \n  [[Project]](https:\u002F\u002Fsermanet.github.io\u002Fimitate\u002F)\n  - Dwibedi, Debidatta and Tompson, Jonathan and Lynch, Corey and Sermanet, Pierre. *IROS 2018* \n  \n- Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1808.00928) \n  [[Project]](https:\u002F\u002Fsites.google.com\u002Fview\u002Factionablerepresentations\u002F)\n  - Andy Zeng, Shuran Song, Stefan Welker, Johnny Lee, Alberto Rodriguez, Thomas Funkhouser. *IROS 2018* \n  \n- Visual Reinforcement Learning with Imagined Goals.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1807.04742) \n  [[Project]](https:\u002F\u002Fsites.google.com\u002Fsite\u002Fvisualrlwithimaginedgoals\u002F)\n  - Ashvin Nair*, Vitchyr Pong*, Murtaza Dalal, Shikhar Bahl, Steven Lin, Sergey Levine.*NeurIPS 2018*\n\n- Grasp2Vec: Learning Object Representations from Self-Supervised Grasping.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1811.06964.pdf) \n  [[Project]](https:\u002F\u002Fsites.google.com\u002Fsite\u002Fgrasp2vec\u002Fhome)\n  - Eric Jang*, Coline Devin*, Vincent Vanhoucke, Sergey Levine. *CoRL 2018*\n\n- Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1810.03043.pdf) \n  [[Project]](https:\u002F\u002Fsites.google.com\u002Fview\u002Frobustness-via-retrying)\n  - Frederik Ebert, Sudeep Dasari, Alex X. Lee, Sergey Levine, Chelsea Finn. *CoRL 2018*\n\n### 2019\n- Learning Long-Range Perception Using Self-Supervision from Short-Range Sensors and Odometry.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1809.07207)\n  - Mirko Nava, Jerome Guzzi, R. Omar Chavez-Garcia, Luca M. Gambardella, Alessandro Giusti. *Robotics and Automation Letters*\n\n- Learning Latent Plans from Play. \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.01973.pdf) \n  [[Project]](https:\u002F\u002Flearning-from-play.github.io\u002F)\n  - Corey Lynch, Mohi Khansari, Ted Xiao, Vikash Kumar, Jonathan Tompson, Sergey Levine, Pierre Sermanet\n\n- Self-Supervised Visual Terrain Classification from Unsupervised Acoustic Feature Learning. \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1912.03227.pdf) \n  - Jannik Zuern, Wolfram Burgard, Abhinav Valada\n\n### 2020\n- Adversarial Skill Networks: Unsupervised Robot Skill Learning from Video.\n[[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.09430.pdf) \n  [[Project]](http:\u002F\u002Frobotskills.cs.uni-freiburg.de\u002F)\n  - Oier Mees, Markus Merklinger, Gabriel Kalweit, Wolfram Burgard *ICRA 2020*\n\n### 2023\n- Self-Supervised Object Goal Navigation with In-Situ Finetuning.\n[[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2212.05923) \n[[Video]](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=LXsZst5ZUpU)\n  - So Yeon Min, Yao-Hung Hubert Tsai, Wei Ding, Ali Farhadi, Ruslan Salakhutdinov, Yonatan Bisk, Jian Zhang *IROS 2023*\n\n### 2024\n- Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2402.02500.pdf)\n  - Haoyi Zhu, Yating Wang, Di Huang, Weicai Ye, Wanli Ouyang, Tong He\n\n## NLP\n- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1810.04805)\n  [[link]](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fbert)\n  - Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova. *NAACL 2019 Best Long Paper*\n\n- Self-Supervised Dialogue Learning\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1907.00448.pdf)\n  - Jiawei Wu, Xin Wang, William Yang Wang. *ACL 2019*\n\n- Self-Supervised Learning for Contextualized Extractive Summarization\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1906.04466.pdf)\n  - Hong Wang, Xin Wang, Wenhan Xiong, Mo Yu, Xiaoxiao Guo, Shiyu Chang, William Yang Wang. *ACL 2019*\n  \n- A Mutual Information Maximization Perspective of Language Representation Learning \n  [[pdf]](https:\u002F\u002Fopenreview.net\u002Fpdf?id=Syx79eBKwr)\n  - Lingpeng Kong, Cyprien de Masson d'Autume, Lei Yu, Wang Ling, Zihang Dai, Dani Yogatama. *ICLR 2020*\n\n- VL-BERT: Pre-training of Generic Visual-Linguistic Representations\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1908.08530.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fjackroos\u002FVL-BERT)\n  - Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, Jifeng Dai. *ICLR 2020*\n\n- A Simple and Effective Self-Supervised Contrastive Learning Framework for Aspect Detection\n  [[pdf]](https:\u002F\u002Fpeople.cs.vt.edu\u002F~reddy\u002Fpapers\u002FAAAI21.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Ftshi04\u002FAspDecSSCL)\n  - Tian Shi, Liuqing Li, Ping Wang, and Chandan K. Reddy. *AAAI 2021*\n\n- Self-Guided Contrastive Learning for BERT Sentence Representations\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.07345)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fgalsang\u002FSG-BERT)\n  - Taeuk Kim, Kang Min Yoo, and Sang-goo Lee. *ACL 2021*\n\n## ASR\n- wav2vec: Unsupervised Pre-Training for Speech Recognition\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1904.05862.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fpytorch\u002Ffairseq\u002Ftree\u002Fmaster\u002Fexamples\u002Fwav2vec)\n  - Steffen Schneider, Alexei Baevski, Ronan Collobert, Michael Auli. *INTERSPEECH 2019*\n\n- Learning Robust and Multilingual Speech Representations\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2001.11128.pdf)\n  - Kazuya Kawakami, Luyu Wang, Chris Dyer, Phil Blunsom, Aaron van den Oord. *Findings of EMNLP 2020*\n\n- Unsupervised Pretraining Transfers Well Across Languages\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2002.02848.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002FCPC_audio)\n  - Morgane Riviere, Armand Joulin, Pierre-Emmanuel Mazare, Emmanuel Dupoux. *ICASSP 2020*\n\n- vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.05453)\n  - Alexei Baevski, Steffen Schneider, Michael Auli. *ICLR 2020*\n\n- Effectiveness of Self-supervised Pre-training for Speech Recognition\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1911.03912.pdf)\n  - Alexei Baevski, Michael Auli, Abdelrahman Mohamed. *ICASSP 2020*\n\n- Towards Unsupervised Speech Recognition and Synthesis with Quantized Speech Representation Learning\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.12729)\n  - Alexander H. Liu, Tao Tu, Hung-yi Lee, Lin-shan Lee. *ICASSP 2020*\n\n- Self-Training for End-to-End Speech Recognition\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1909.09116)\n  - Jacob Kahn, Ann Lee, Awni Hannun. *ICASSP 2020*\n\n- Generative Pre-Training for Speech with Autoregressive Predictive Coding\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.12607.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fiamyuanchung\u002FAutoregressive-Predictive-Coding)\n  - Yu-An Chung, James Glass. *ICASSP 2020*\n\n- Disentangled Speech Embeddings using Cross-modal Self-supervision\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2002.08742v1.pdf)\n  - Arsha Nagrani, Joon Son Chung, Samuel Albanie, Andrew Zisserman. *ICASSP 2020*\n\n- Multi-task Self-supervised Learning for Robust Speech Recognition\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2001.09239.pdf)\n  - Mirco Ravanelli, Jianyuan Zhong, Santiago Pascual, Pawel Swietojanski, Joao Monteiro, Jan Trmal, Yoshua Bengio. *ICASSP 2020*\n\n- Visually Guided Self Supervised Learning of Speech Representations\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2001.04316.pdf)\n  - Abhinav Shukla, Konstantinos Vougioukas, Pingchuan Ma, Stavros Petridis, Maja Pantic. *ICASSP 2020*\n\n- Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.12638)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fs3prl\u002Fs3prl)\n  - Andy T. Liu, Shu-wen Yang, Po-Han Chi, Po-chun Hsu, Hung-yi Lee. *ICASSP 2020*\n\n- Vector-Quantized Autoregressive Predictive Coding\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.08392)\n  [[code]](https:\u002F\u002Fgithub.com\u002FAlexander-H-Liu\u002FNPC)\n  - Yu-An Chung, Hao Tang, James Glass. *Interspeech 2020*\n\n- wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.11477)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fpytorch\u002Ffairseq\u002Ftree\u002Fmaster\u002Fexamples\u002Fwav2vec)\n  - Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, Michael Auli. *NeurIPS 2020*\n\n- Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.01027)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fpytorch\u002Ffairseq\u002Ftree\u002Fmaster\u002Fexamples\u002Fwav2vec)\n  - Wei-Ning Hsu, Anuroop Sriram, Alexei Baevski, Tatiana Likhomanenko, Qiantong Xu, Vineel Pratap, Jacob Kahn, Ann Lee, Ronan Collobert, Gabriel Synnaeve, Michael Auli\n\n- HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.07447)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fpytorch\u002Ffairseq\u002Ftree\u002Fmaster\u002Fexamples\u002Fhubert)\n  - Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhutdinov, Abdelrahman Mohamed. *ICASSP 2021*\n\n- Unsupervised Speech Recognition\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2105.11084)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fpytorch\u002Ffairseq\u002Ftree\u002Fmaster\u002Fexamples\u002Fwav2vec\u002Funsupervised)\n  - Alexei Baevski, Wei-Ning Hsu, Alexis Conneau, Michael Auli\n\n- TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.06028)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fs3prl\u002Fs3prl)\n  - Andy T. Liu, Shang-Wen Li, Hung-yi Lee. *IEEE\u002FACM TASLP 2021*\n\n- Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependencies\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.00406)\n  [[code]](https:\u002F\u002Fgithub.com\u002FAlexander-H-Liu\u002FNPC)\n  - Alexander H. Liu, Yu-An Chung, James Glass. *Interspeech 2021*\n\n## Time-Series\n - Unsupervised Scalable Representation Learning for Multivariate Time Series\n   [[pdf]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Ffile\u002F53c6de78244e9f528eb3e1cda69699bb-Paper.pdf)\n   [[code]](https:\u002F\u002Fgithub.com\u002FWhite-Link\u002FUnsupervisedScalableRepresentationLearningTimeSeries)\n   - Franceschi, Jean-Yves, Aymeric Dieuleveut, and Martin Jaggi. *NeurIPS 2019*\n \n - Time-Series Representation Learning via Temporal and Contextual Contrasting\n   [[pdf]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0324.pdf)\n   [[code]](https:\u002F\u002Fgithub.com\u002Femadeldeen24\u002FTS-TCC)\n   - Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee Keong Kwoh, Xiaoli Li, and Cuntai Guan. *IJCAI 2021*\n \n - Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding\n   [[pdf]](https:\u002F\u002Fopenreview.net\u002Fpdf?id=8qDwejCuCN)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fsanatonek\u002FTNC_representation_learning)\n   - Tonekaboni, Sana, Danny Eytan, and Anna Goldenberg. *ICLR 2021*\n \n - A Transformer-Based Framework for Multivariate Time Series Representation Learning\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2010.02803.pdf)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fgzerveas\u002Fmvts_transformer)\n   - Zerveas, George, Srideepika Jayaraman, Dhaval Patel, Anuradha Bhamidipaty, and Carsten Eickhoff. *KDD 2021*\n\n- TS2Vec: Towards Universal Representation of Time Series\n   [[pdf]](https:\u002F\u002Fwww.aaai.org\u002FAAAI22Papers\u002FAAAI-8809.YueZ.pdf)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fyuezhihan\u002Fts2vec)\n   - Zerveas, George, Srideepika Jayaraman, Dhaval Patel, Anuradha Bhamidipaty, and Carsten Eickhoff. *AAAI 2022*\n \n\n\n## Graph\n - Deep Graph Infomax\n   [[pdf]](https:\u002F\u002Fopenreview.net\u002Fforum?id=rklz9iAcKQ)\n   [[code]](https:\u002F\u002Fgithub.com\u002FPetarV-\u002FDGI)\n   - Petar Veličković, William Fedus, William L. Hamilton, Pietro Liò, Yoshua Bengio, R Devon Hjelm. *ICLR 2019*\n \n - When Does Self-Supervision Help Graph Convolutional Networks\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.09136.pdf)\n   - Yuning You, Tianlong Chen, Zhangyang Wang, Yang Shen. *ICML 2020*\n   \n - Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labels\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1902.11038v2.pdf)\n   - Ke Sun, Zhouchen Lin, Zhanxing Zhu. *AAAI 2020*\n   \n - Gaining insight into SARS-CoV-2 infection and COVID-19 severity using self-supervised edge features and Graph Neural Networks\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.12971v1.pdf)\n   - Arijit Sehanobish, Neal G. Ravindra, David van Dijk. *ICML 2020 Workshop*\n   \n - Deep Graph Contrastive Representation Learning\n    [[pdf]](http:\u002F\u002Farxiv.org\u002Fabs\u002F2006.04131)\n    [[code]](https:\u002F\u002Fgithub.com\u002FCRIPAC-DIG\u002FGRACE)\n   - Yanqiao Zhu, Yichen Xu, Feng Yu, Qiang Liu, Shu Wu, Liang Wang. *ICML 2020 Workshop*\n   \n - Contrastive Multi-View Representation Learning on Graphs\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.05582)\n   - Kaveh Hassani, Amir Hosein Khasahmadi. *ICML 2020*\n   \n - GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.09963.pdf)\n   - Jiezhong Qiu, Qibin Chen, Yuxiao Dong. *KDD 2020*\n   \n - GPT-GNN: Generative Pre-Training of Graph Neural Networks\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.15437.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002Facbull\u002FGPT-GNN)\n   - Ziniu Hu, Yuxiao Dong, Kuansan Wang, Kai-Wei Chang, Yizhou Sun. *KDD 2020*\n   \n - Self-supervised Learning on Graphs: Deep Insights and New Direction\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.10141.pdf)\n   - Wei Jin, Tyler Derr, Haochen Liu, Yiqi Wang, Suhang Wang, Zitao Liu, Jiliang Tang.\n\n- Self-Supervised Learning of Contextual Embeddings for Link Prediction in Heterogeneous Networks\n  [[pdf]](https:\u002F\u002Fpeople.cs.vt.edu\u002F~reddy\u002Fpapers\u002FWWW21.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fpnnl\u002FSLICE)\n  - Ping Wang, Khushbu Agarwal, Colby Ham, Sutanay Choudhury, and Chandan K. Reddy. *WWW 2021*\n\n- Self-Supervised Hyperboloid Representations from Logical Queries over Knowledge Graphs\n  [[pdf]](https:\u002F\u002Fpeople.cs.vt.edu\u002F~reddy\u002Fpapers\u002FWWW21a.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Famazon-research\u002Fhyperbolic-embeddings)\n  - Nurendra Choudhary, Nikhil Rao, Sumeet Katariya, Karthik Subbian, and Chandan K. Reddy. *WWW 2021*\n\n- GraphMAE: Self-supervised Masked Graph Autoencoders\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2205.10803.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002FTHUDM\u002FGraphMAE)\n  - Zhenyu Hou, Xiao Liu, Yukuo Ceng, Yuxiao Dong, Hongxia Yang, Chunjie Wang, Jie Tang. *KDD 2022*\n\n## Talks\n- The power of Self-Learning Systems. Demis Hassabis (DeepMind).\n  [[link]](https:\u002F\u002Fyoutu.be\u002Fwxis9FrCHbw)\n- Supersizing Self-Supervision: Learning Perception and Action without Human Supervision. Abhinav Gupta (CMU).\n  [[link]](https:\u002F\u002Fsimons.berkeley.edu\u002Ftalks\u002Fabhinav-gupta-2017-3-28)\n- Self-supervision, Meta-supervision, Curiosity: Making Computers Study Harder. Alyosha Efros (UCB) \n  [[link]](https:\u002F\u002Fbusiness.facebook.com\u002Facademics\u002Fvideos\u002F1632981350086599)\n- Unsupervised Visual Learning Tutorial. *CVPR 2018* \n  [[part 1]](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=gSqmUOAMwcc) \n  [[part 2]](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=BijK_US6A0w)\n- Self-Supervised Learning. Andrew Zisserman (Oxford & Deepmind). \n  [[pdf]](https:\u002F\u002Fproject.inria.fr\u002Fpaiss\u002Ffiles\u002F2018\u002F07\u002Fzisserman-self-supervised.pdf)\n- Graph Embeddings, Content Understanding, & Self-Supervised Learning. Yann LeCun. (NYU & FAIR)\n  [[pdf]](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F12pDCno02FJPDEBk4iGuuaj8b2rr48Hh0\u002Fview)\n  [[video]](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=UGPT64wo7lU)\n- Self-supervised learning: could machines learn like humans? Yann LeCun @EPFL. \n  [[video]](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=7I0Qt7GALVk)\n- Week 9 (b): CS294-158 Deep Unsupervised Learning(Spring 2019). Alyosha Efros @UC Berkeley. \n  [[video]](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=PX11C5Vfo9U)\n\n## Thesis\n- Supervision Beyond Manual Annotations for Learning Visual Representations. Carl Doersch. [[pdf]](http:\u002F\u002Fwww.carldoersch.com\u002Fdocs\u002Fthesis.pdf).\n- Image Synthesis for Self-Supervised Visual Representation Learning. Richard Zhang. [[pdf]](https:\u002F\u002Fwww2.eecs.berkeley.edu\u002FPubs\u002FTechRpts\u002F2018\u002FEECS-2018-36.pdf).\n- Visual Learning beyond Direct Supervision. Tinghui Zhou. [[pdf]](https:\u002F\u002Fwww2.eecs.berkeley.edu\u002FPubs\u002FTechRpts\u002F2018\u002FEECS-2018-128.pdf).\n- Visual Learning with Minimal Human Supervision. Ishan Misra. [[pdf]](https:\u002F\u002Fwww.ri.cmu.edu\u002Fpublications\u002Fvisual-learning-with-minimal-human-supervision\u002F).\n\n## Blog\n- Self-Supervised Representation Learning. Lilian Weng. [[link]](https:\u002F\u002Flilianweng.github.io\u002Flil-log\u002F2019\u002F11\u002F10\u002Fself-supervised-learning.html).\n- Self Supervised Representation Learning in NLP. Amit Chaudhary. [[link]](https:\u002F\u002Famitness.com\u002F2020\u002F05\u002Fself-supervised-learning-nlp\u002F).\n- The Illustrated [[Self-Supervised Learning]](https:\u002F\u002Famitness.com\u002F2020\u002F02\u002Fillustrated-self-supervised-learning\u002F), [[SimCLR]](https:\u002F\u002Famitness.com\u002F2020\u002F03\u002Fillustrated-simclr\u002F), [[PIRL]](https:\u002F\u002Famitness.com\u002F2020\u002F03\u002Fillustrated-pirl\u002F), [[Self-Labelling]](https:\u002F\u002Famitness.com\u002F2020\u002F04\u002Fillustrated-self-labelling\u002F), [[FixMatch]](https:\u002F\u002Famitness.com\u002F2020\u002F03\u002Ffixmatch-semi-supervised\u002F), [[DeepCluster]](https:\u002F\u002Famitness.com\u002F2020\u002F04\u002Fdeepcluster\u002F). Amit Chaudhary. \n- Contrastive Self-Supervised Learning. Ankesh Anand. [[link]](https:\u002F\u002Fankeshanand.com\u002Fblog\u002F2020\u002F01\u002F26\u002Fcontrative-self-supervised-learning.html).\n\n\n## License\nTo the extent possible under law, [Zhongzheng Ren](https:\u002F\u002Fjason718.github.io\u002F) has waived all copyright and related or neighboring rights to this work.\n","# 令人惊叹的自监督学习[![Awesome](https:\u002F\u002Fawesome.re\u002Fbadge.svg)](https:\u002F\u002Fawesome.re)\n\n一份精心整理的自监督学习资源清单。灵感来源于 [awesome-deep-vision](https:\u002F\u002Fgithub.com\u002Fkjw0612\u002Fawesome-deep-vision)、[awesome-adversarial-machine-learning](https:\u002F\u002Fgithub.com\u002Fyenchenlin\u002Fawesome-adversarial-machine-learning)、[awesome-deep-learning-papers](https:\u002F\u002Fgithub.com\u002Fterryum\u002Fawesome-deep-learning-papers) 以及 [awesome-architecture-search](https:\u002F\u002Fgithub.com\u002Fmarkdtw\u002Fawesome-architecture-search)。\n\n#### 为什么选择自监督学习？\n自监督学习已成为人工智能领域中一个令人振奋的方向。\n  - 吉滕德拉·马利克：“监督是人工智能研究者的鸦片”\n  - 阿廖沙·埃弗罗斯：“人工智能革命不会依赖于监督”\n  - 扬·勒丘恩：“自监督学习是蛋糕本身，有监督学习只是蛋糕上的糖霜，而强化学习则是蛋糕上的樱桃”\n\n## 贡献\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjason718_awesome-self-supervised-learning_readme_7a9f4b7eebd0.jpg\" alt=\"我们需要你！\">\n\u003C\u002Fp>\n\n请通过 [pull request](https:\u002F\u002Fgithub.com\u002Fjason718\u002FAwesome-Self-Supervised-Learning\u002Fpulls) 帮助完善这份列表。\n\nMarkdown 格式：\n```markdown\n- 论文名称。\n  [[pdf]](链接)\n  [[代码]](链接)\n  - 作者1、作者2和作者3。 *会议年份*\n```\n\n## 目录\n- [理论](#theory)\n- [计算机视觉 (CV)](#computer-vision)\n  - [综述](#survey)\n  - [图像表征学习](#image-representation-learning)\n  - [视频表征学习](#video-representation-learning)\n  - [3D 特征学习](#3D-feature-learning)\n  - [几何](#geometry)\n  - [音频](#audio)\n  - [其他](#others)\n- [机器学习](#machine-learning)\n  - [强化学习](#reinforcement-learning)\n  - [推荐系统](#recommendation-systems)\n- [机器人学](#robotics)  \n- [自然语言处理 (NLP)](#nlp)\n- [自动语音识别 (ASR)](#asr)\n- [时间序列](#Time-Series)\n- [图](#graph)\n- [讲座](#talks)\n- [论文](#thesis)\n- [博客](#blog)\n\n\n\n## 理论\n\n#### 2019年\n-   对比无监督表征学习的理论分析。\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1902.09229.pdf)\n    -   Sanjeev Arora、Hrishikesh Khandeparkar、Mikhail Khodak、Orestis Plevrakis 和 Nikunj Saunshi。 *ICML 2019*\n#### 2020年\n-   从超球面上的对齐与均匀性理解对比表征学习。\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2005.10242)\n    -   Tongzhou Wang、Phillip Isola。 *ICML 2020*\n-   通过双深度网络理解自监督学习。\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2010.00578.pdf)\n    -   Yuandong Tian、Lantao Yu、Xinlei Chen 和 Surya Ganguli。\n-   对于自监督学习而言，理性意味着泛化，这一点已被证明。\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2010.08508.pdf)\n    -   Yamini Bansal、Gal Kaplun 和 Boaz Barak。\n   \n#### 2021年\n-   朝向对比自监督学习的泛化。\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2111.00743.pdf)\n    -   Weiran Huang、Mingyang Yi 和 Xuyang Zhao。\n-   理解对比损失的行为。\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2012.09740.pdf)\n    -   Feng Wang 和 Huaping Liu。 *CVPR 2021*\n-   预测你已知的内容有所帮助：可证明的自监督学习。\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2008.01064.pdf)\n    -   Jason D. Lee、Qi Lei、Nikunj Saunshi 和 Jiacheng Zhuo。\n-   对比学习、多视角冗余与线性模型。\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2008.10150.pdf)\n    -   Christopher Tosh、Akshay Krishnamurthy 和 Daniel Hsu。\n-   对比学习反转了数据生成过程。\n    [[pdf]](Contrastive Learning Inverts the Data Generating Process)\n    -   Roland S. Zimmermann、Yash Sharma、Steffen Schneider、Matthias Bethge、Wieland Brendel。 **ICML 2021**\n\n\n#### 2022年\n-   对比学习可以为近似视不变函数找到最优基。\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2103.03568.pdf)\n    -   Jiaye Teng、Weiran Huang 和 Haowei He。 *AISTATS 2022*\n\n#### 2023年\n-   基于前置任务的自监督学习能否被下游数据增强？一项理论分析。\n    [[pdf]](https:\u002F\u002Fopenreview.net\u002Fpdf?id=AjC0KBjiMu)\n    -   Daniel D. Johnson、Ayoub El Hanchi 和 Chris J. Maddison。 *ICLR 2023*\n-   关于自监督学习的分步性质。\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2303.15438)\n    -   James B. Simon、Maksis Knutins、Liu Ziyin、Daniel Geisz、Abraham J. Fetterman、Joshua Albrecht。 *ICML 2023*\n-   自监督学习的损失景观由什么塑造？\n    [[pdf]](https:\u002F\u002Fopenreview.net\u002Fpdf?id=3zSn48RUO8M)\n    -   Liu Ziyin、Ekdeep Singh Lubana、Masahito Ueda、Hidenori Tanaka。 *ICLR 2023*\n\n\n#### 2024年  \n-   在对比学习中连接小批量与渐近分析：从 InfoNCE 到基于核的损失。\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2405.18045)\n    [[代码]](https:\u002F\u002Fgithub.com\u002Fpakoromilas\u002FDHEL-KCL)\n    -   Panagiotis Koromilas、Giorgos Bouritsas、Theodoros Giannakopoulos、Mihalis Nicolaou、Yannis Panagakis。 *ICML 2024*\n-   自监督学习中的矩阵信息论。\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2305.17326)\n    -   Yifan Zhang、Zhiquan Tan、Jingqin Yang、Weiran Huang、Yang Yuan。 *ICML 2024*\n-   自监督学习中的信息流。\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2309.17281)\n    -   Zhiquan Tan、Jingqin Yang、Weiran Huang、Yang Yuan、Yifan Zhang。 *ICML 2024*\n\n\n       \n## 计算机视觉\n### 综述\n- 对比表征学习：框架与综述\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.05113)\n  - Phuc H. Le-Khac、Graham Healy、Alan F. Smeaton。 *IEEE Access 2020*\n\n- 对比自监督学习综述\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2011.00362.pdf)\n  - Ashish Jaiswal、Ashwin R Babu、Mohammad Z Zadeh、Debapriya Banerjee、Fillia Makedon\n\n- 使用深度神经网络进行自监督视觉特征学习：综述。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1902.06162.pdf)\n  - Longlong Jing 和 Yingli Tian。 *T-PAMI 2020*\n\n- 自监督学习：生成式还是对比式\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.08218.pdf)\n  - Xiao Liu、Fanjin Zhang、Zhenyu Hou、Li Mian、Zhaoyu Wang、Jing Zhang、Jie Tang。 *TKDE 2021*\n\n- 了解你的自监督学习：基于图像的生成式与判别式训练综述\n  [[pdf]](https:\u002F\u002Fopenreview.net\u002Fpdf?id=Ma25S4ludQ)\n  - Utku Ozbulak、Hyun Jung Lee、Beril Boga、Esla Timothy Anzaku、Ho-min Park、Arnout Van Messem、Wesley De Neve、Joris Vankerschaver。 *TMLR 2023*\n\n\n### 图像表征学习\n\n#### 基准代码\n- FAIR 自监督基准 [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.01235) [[仓库]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Ffair_self_supervision_benchmark)：用于评估各种自监督方法所学习到的视觉表征质量的各种基准（及遗留）任务。\n\n- 自监督模型的迁移性能如何？[[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.13377) [[repo]](https:\u002F\u002Fgithub.com\u002Flinusericsson\u002Fssl-transfer)：一个用于评估自监督学习的基准，包含多样本\u002F少样本识别、目标检测、表面法线估计和语义分割任务。\n\n#### 2015年\n- 基于上下文预测的无监督视觉表征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1505.05192)\n  [[code]](http:\u002F\u002Fgraphics.cs.cmu.edu\u002Fprojects\u002FdeepContext\u002F)\n  - Doersch, Carl 和 Gupta, Abhinav 以及 Efros, Alexei A. *ICCV 2015*\n\n- 利用视频进行视觉表征的无监督学习。\n  [[pdf]](http:\u002F\u002Fwww.cs.cmu.edu\u002F~xiaolonw\u002Fpapers\u002Funsupervised_video.pdf) \n  [[code]](http:\u002F\u002Fwww.cs.cmu.edu\u002F~xiaolonw\u002Funsupervise.html)\n  - Wang, Xiaolong 和 Gupta, Abhinav. *ICCV 2015*\n\n- 通过运动来学习“看”的能力。\n  [[pdf]](http:\u002F\u002Farxiv.org\u002Fabs\u002F1505.01596)\n  [[code]](https:\u002F\u002Fpeople.eecs.berkeley.edu\u002F~pulkitag\u002Flsm\u002Flsm.html)\n  - Agrawal, Pulkit、Carreira, Joao 和 Malik, Jitendra. *ICCV 2015*\n\n- 学习与自我运动相关的图像表征。\n  [[pdf]](http:\u002F\u002Fvision.cs.utexas.edu\u002Fprojects\u002Fegoequiv\u002Fijcv_bestpaper_specialissue_egoequiv.pdf) \n  [[code]](http:\u002F\u002Fvision.cs.utexas.edu\u002Fprojects\u002Fegoequiv\u002F)\n  - Jayaraman, Dinesh 和 Grauman, Kristen。*ICCV 2015*\n\n#### 2016年\n- 深度表征与图像聚类的联合无监督学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1604.03628.pdf) \n  [[code-torch]](https:\u002F\u002Fgithub.com\u002Fjwyang\u002FJULE.torch)\n  [[code-caffe]](https:\u002F\u002Fgithub.com\u002Fjwyang\u002FJULE-Caffe)\n  - Jianwei Yang、Devi Parikh 和 Dhruv Batra。*CVPR 2016*\n\n- 用于聚类分析的无监督深度嵌入。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1511.06335.pdf) \n  [[code]](https:\u002F\u002Fgithub.com\u002Fpiiswrong\u002Fdec)\n  - Junyuan Xie、Ross Girshick 和 Ali Farhadi。*ICML 2016*\n\n- 缓慢而稳定的特征分析：视频中的高阶时间一致性。\n  [[pdf]](http:\u002F\u002Fvision.cs.utexas.edu\u002Fprojects\u002Fslowsteady\u002Fcvpr16.pdf)\n  - Jayaraman, Dinesh 和 Grauman, Kristen。*CVPR 2016*\n\n- 上下文编码器：通过修复缺失区域进行特征学习。\n  [[pdf]](https:\u002F\u002Fpeople.eecs.berkeley.edu\u002F~pathak\u002Fpapers\u002Fcvpr16.pdf)\n  [[code]](https:\u002F\u002Fpeople.eecs.berkeley.edu\u002F~pathak\u002Fcontext_encoder\u002F)\n  - Pathak, Deepak、Krahenbuhl, Philipp、Donahue, Jeff、Darrell, Trevor 和 Efros, Alexei A. *CVPR 2016*\n\n- 彩色图像上色。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1603.08511)\n  [[code]](http:\u002F\u002Frichzhang.github.io\u002Fcolorization\u002F)\n  - Zhang, Richard、Isola, Phillip 和 Efros, Alexei A. *ECCV 2016*\n\n- 通过拼图游戏进行视觉表征的无监督学习。\n  [[pdf]](http:\u002F\u002Farxiv.org\u002Fabs\u002F1603.09246)\n  [[code]](http:\u002F\u002Fwww.cvg.unibe.ch\u002Fresearch\u002FJigsawPuzzleSolver.html)\n  - Noroozi, Mehdi 和 Favaro, Paolo。*ECCV 2016*\n\n- 环境声音为视觉学习提供监督信号。\n  [[pdf]](http:\u002F\u002Farxiv.org\u002Fpdf\u002F1608.07017) \n  [[code]](http:\u002F\u002Fandrewowens.com\u002Fambient\u002Findex.html)\n  - Owens, Andrew、Wu, Jiajun、McDermott, Josh、Freeman, William 和 Torralba, Antonio。*ECCV 2016*\n\n- 自动上色的表征学习。\n  [[pdf]](http:\u002F\u002Farxiv.org\u002Fpdf\u002F1603.06668.pdf)\n  [[code]](http:\u002F\u002Fpeople.cs.uchicago.edu\u002F~larsson\u002Fcolorization\u002F)\n  - Larsson, Gustav、Maire, Michael 和 Shakhnarovich, Gregory。*ECCV 2016*\n\n- 基于图的一致性约束的无监督视觉表征学习。\n  [[pdf]](http:\u002F\u002Ffaculty.ucmerced.edu\u002Fmhyang\u002Fpapers\u002Feccv16_feature_learning.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fdongli12\u002FFeatureLearning)\n  - Li, Dong、Hung, Wei-Chih、Huang, Jia-Bin、Wang, Shengjin、Ahuja, Narendra 和 Yang, Ming-Hsuan。*ECCV 2016*\n\n#### 2017年\n- 对抗式特征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1605.09782.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fjeffdonahue\u002Fbigan)\n  - Donahue, Jeff、Krahenbuhl, Philipp 和 Darrell, Trevor。*ICLR 2017*\n\n- 通过将图像嵌入到文本主题空间中进行视觉特征的自监督学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1705.08631.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Flluisgomez\u002FTextTopicNet)\n  - L. Gomez*、Y. Patel*、M. Rusiñol、D. Karatzas 和 C.V. Jawahar。*CVPR 2017*\n\n- 分裂脑自动编码器：通过跨通道预测进行无监督学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1611.09842) \n  [[code]](https:\u002F\u002Fgithub.com\u002Frichzhang\u002Fsplitbrainauto)\n  - Zhang, Richard、Isola, Phillip 和 Efros, Alexei A. *CVPR 2017*\n\n- 通过观察物体运动来学习特征。\n  [[pdf]](https:\u002F\u002Fpeople.eecs.berkeley.edu\u002F~pathak\u002Fpapers\u002Fcvpr17.pdf) \n  [[code]](https:\u002F\u002Fpeople.eecs.berkeley.edu\u002F~pathak\u002Funsupervised_video\u002F)\n  - Pathak, Deepak、Girshick, Ross、Dollar, Piotr、Darrell, Trevor 和 Hariharan, Bharath。*CVPR 2017*\n\n- 上色作为视觉理解的代理任务。\n  [[pdf]](http:\u002F\u002Farxiv.org\u002Fabs\u002F1703.04044) \n  [[code]](http:\u002F\u002Fpeople.cs.uchicago.edu\u002F~larsson\u002Fcolor-proxy\u002F)\n  - Larsson, Gustav、Maire, Michael 和 Shakhnarovich, Gregory。*CVPR 2017*\n\n- DeepPermNet：视觉排列学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1704.02729.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Frfsantacruz\u002Fdeep-perm-net)\n  - Cruz, Rodrigo Santa、Fernando, Basura、Cherian, Anoop 和 Gould, Stephen。*CVPR 2017*\n\n- 通过预测噪声进行无监督学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1704.05310) \n  [[code]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fnoise-as-targets)\n  - Bojanowski, Piotr 和 Joulin, Armand。*ICML 2017*\n\n- 多任务自监督视觉学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1708.07860)\n  - Doersch, Carl 和 Zisserman, Andrew。*ICCV 2017*\n\n- 通过学习计数来进行表征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1708.06734)\n  - Noroozi, Mehdi、Pirsiavash, Hamed 和 Favaro, Paolo。*ICCV 2017*\n\n- 自监督视觉表征学习中的传递不变性。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1708.02901.pdf)\n  - Wang, Xiaolong、He, Kaiming 和 Gupta, Abhinav。*ICCV 2017*\n\n- 看、听并学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1705.08168.pdf)\n  - Relja, Arandjelovic 和 Zisserman, Andrew。*ICCV 2017*\n\n- 通过排序序列进行无监督表征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1708.01246.pdf) \n  [[code]](https:\u002F\u002Fgithub.com\u002FHsinYingLee\u002FOPN)\n  - Hsin-Ying Lee、Jia-Bin Huang、Maneesh Kumar Singh 和 Ming-Hsuan Yang。*ICCV 2017*\n\n#### 2018年\n- 基于非参数实例判别的无监督特征学习\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1805.01978.pdf) \n  [[code]](https:\u002F\u002Fgithub.com\u002Fzhirongw\u002Flemniscate.pytorch)\n  - Zhirong Wu、Yuanjun Xiong、X Yu Stella 和 Dahua Lin。*CVPR 2018*\n\n- 通过完成受损拼图学习图像表示。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1802.01880.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002FMehdiNoroozi\u002FJigsawPuzzleSolver)\n  - Kim, Dahun、Cho, Donghyeon、Yoo, Donggeun 和 Kweon, In So。*WACV 2018*\n\n- 通过预测图像旋转进行无监督表征学习。\n  [[pdf]](https:\u002F\u002Fopenreview.net\u002Fforum?id=S1v4N2l0-)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fgidariss\u002FFeatureLearningRotNet)\n  - Spyros Gidaris、Praveer Singh 和 Nikos Komodakis。*ICLR 2018*\n\n- 通过伪监督和基于图的活动正则化，在神经网络中学习用于聚类的潜在表征。\n  [[pdf]](https:\u002F\u002Fopenreview.net\u002Fpdf?id=HkMvEOlAb) \n  [[code]](https:\u002F\u002Fgithub.com\u002Fozcell\u002FLALNets)\n  - Ozsel Kilinc 和 Ismail Uysal。*ICLR 2018*\n\n- 基于上下文的自监督学习的改进。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1711.06379)\n  - Terrell Mundhenk、Daniel Ho 和 Barry Chen。*CVPR 2018*\n\n- 通过学习识别伪影进行自监督特征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1806.05024.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fsjenni\u002FLearningToSpotArtifacts)\n  - Simon Jenni、伯尔尼大学和Paolo Favaro。*CVPR 2018*\n\n- 通过知识迁移提升自监督学习。\n  [[pdf]](https:\u002F\u002Fwww.csee.umbc.edu\u002F~hpirsiav\u002Fpapers\u002Ftransfer_cvpr18.pdf)\n  - Mehdi Noroozi、Ananth Vinjimoor、Paolo Favaro 和 Hamed Pirsiavash。*CVPR 2018*\n\n- 利用合成图像进行跨域自监督多任务特征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1711.09082)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fjason718\u002Fgame-feature-learning)\n  - Zhongzheng Ren 和 Yong Jae Lee。*CVPR 2018*\n\n- ShapeCodes：通过将视图提升为视图网格进行自监督特征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.00505.pdf)\n  - Dinesh Jayaraman*，加州大学伯克利分校；Ruohan Gao，德克萨斯大学奥斯汀分校；Kristen Grauman。*ECCV 2018*\n\n- 用于视觉特征无监督学习的深度聚类\n    [[pdf]](https:\u002F\u002Fresearch.fb.com\u002Fwp-content\u002Fuploads\u002F2018\u002F09\u002FDeep-Clustering-for-Unsupervised-Learning-of-Visual-Features.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fdeepcluster)\n    - Mathilde Caron、Piotr Bojanowski、Armand Joulin、Matthijs Douze。*ECCV 2018*\n\n- 基于跨像素光流相似性的自监督学习。\n  [[pdf]](http:\u002F\u002Fwww.robots.ox.ac.uk\u002F~vgg\u002Fpublications\u002F2018\u002FMahendran18\u002Fmahendran18.pdf)\n  - Aravindh Mahendran、James Thewlis、Andrea Vedaldi。*ACCV 2018*\n\n#### 2019年\n- 基于对比预测编码的表征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1807.03748)\n  - Aaron van den Oord、Yazhe Li、Oriol Vinyals。\n\n- 通过条件运动传播进行自监督学习。\n  [[pdf]](\u003Chttps:\u002F\u002Farxiv.org\u002Fabs\u002F1903.11412>)\n  [[code]](https:\u002F\u002Fgithub.com\u002FXiaohangZhan\u002Fconditional-motion-propagation)\n  - Xiaohang Zhan、Xingang Pan、Ziwei Liu、Dahua Lin 和 Chen Change Loy。*CVPR 2019*\n\n- 通过旋转特征解耦进行自监督表征学习。\n  [[pdf]](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_CVPR_2019\u002Fhtml\u002FFeng_Self-Supervised_Representation_Learning_by_Rotation_Feature_Decoupling_CVPR_2019_paper.html)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fphiliptheother\u002FFeatureDecoupling)\n  - Zeyu Feng、Chang Xu、Dacheng Tao。*CVPR 2019*\n\n- 重新审视自监督视觉表征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1901.09005)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fgoogle\u002Frevisiting-self-supervised)\n  - Alexander Kolesnikov、Xiaohua Zhai、Lucas Beye。*CVPR 2019*\n\n- 基于辅助旋转损失的自监督GAN。\n  [[pdf]](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_CVPR_2019\u002Fpapers\u002FChen_Self-Supervised_GANs_via_Auxiliary_Rotation_Loss_CVPR_2019_paper.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fvandit15\u002FSelf-Supervised-Gans-Pytorch)\n  - Ting Chen、Xiaohua Zhai、Marvin Ritter、Mario Lucic、Neil Houlsby。*CVPR 2019*\n\n- AET与AED：通过自动编码变换而非数据进行无监督表征学习。\n  [[pdf]](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_CVPR_2019\u002Fpapers\u002FZhang_AET_vs._AED_Unsupervised_Representation_Learning_by_Auto-Encoding_Transformations_Rather_CVPR_2019_paper.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fmaple-research-lab\u002FAET)\n  - Liheng Zhang、Guo-Jun Qi、Liqiang Wang、Jiebo Luo。*CVPR 2019*\n\n- 通过邻域发现进行无监督深度学习。\n  [[pdf]](http:\u002F\u002Fproceedings.mlr.press\u002Fv97\u002Fhuang19b.html)。\n  [[code]](https:\u002F\u002Fgithub.com\u002FRaymond-sci\u002FAND)\n  - Jiabo Huang、Qi Dong、Shaogang Gong、Xiatian Zhu。*ICML 2019*\n\n- 对比多视图编码。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.05849)\n  [[code]](https:\u002F\u002Fgithub.com\u002FHobbitLong\u002FCMC\u002F)\n  - Yonglong Tian、Dilip Krishnan 和 Phillip Isola。\n\n- 大规模对抗性表征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1907.02544)\n  - Jeff Donahue、Karen Simonyan。\n\n- 通过最大化跨视图互信息来学习表征。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1906.00910)\n  [[code]](https:\u002F\u002Fgithub.com\u002FPhilip-Bachman\u002Famdim-public)\n  - Philip Bachman、R Devon Hjelm、William Buchwalter。\n\n- Selfie：用于图像嵌入的自监督预训练。\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.02940) \n    - Trieu H. Trinh、Minh-Thang Luong、Quoc V. Le\n\n- 基于对比预测编码的数据高效图像识别\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.09272)\n    - Olivier J. He ́naff、Ali Razavi、Carl Doersch、S. M. Ali Eslami、Aaron van den Oord。\n\n- 使用自监督学习可以提高模型的鲁棒性和不确定性估计\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1906.12340)\n    [[code]](https:\u002F\u002Fgithub.com\u002Fhendrycks\u002Fss-ood)\n    - Dan Hendrycks、Mantas Mazeika、Saurav Kadavath、Dawn Song。*NeurIPS 2019*\n\n- 通过自监督提升少样本视觉学习\n    [[pdf]](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ICCV_2019\u002Fpapers\u002FGidaris_Boosting_Few-Shot_Visual_Learning_With_Self-Supervision_ICCV_2019_paper.pdf)\n    - Pyros Gidaris、Andrei Bursuc、Nikos Komodakis、Patrick Pérez 和 Matthieu Cord。*ICCV 2019*\n\n- 基于元辅助学习的自监督泛化\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1901.08933.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002Florenmt\u002Fmaxl)\n    - Shikun Liu、Andrew J. Davison、Edward Johns。*NeurIPS 2019*\n\n- 用于表征学习的瓦瑟斯坦依赖度量\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.11780.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002FSeongokRyu\u002Fmutual_information_and_self-supervised_learning\u002Ftree\u002Fmaster\u002Fpredictive_coding)\n    - Sherjil Ozair、Corey Lynch、Yoshua Bengio、Aaron van den Oord、Sergey Levine、Pierre Sermanet。*NeurIPS 2019*\n\n- 自监督视觉表征学习的扩展与基准测试\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.01235)\n    [[code]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Ffair_self_supervision_benchmark)\n    - Priya Goyal、Dhruv Mahajan、Abhinav Gupta、Ishan Misra。*ICCV 2019*\n\n- 在非精选数据上进行图像特征的无监督预训练\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1905.01278.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002FDeeperCluster)\n    - Mathilde Caron, Piotr Bojanowski, Julien Mairal, Armand Joulin. *ICCV 2019 口头报告*\n\n- S4L：自监督半监督学习\n  [[pdf]](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ICCV_2019\u002Fpapers\u002FZhai_S4L_Self-Supervised_Semi-Supervised_Learning_ICCV_2019_paper.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fs4l)\n  - Xiaohua Zhai, Avital Oliver, Alexander Kolesnikov, Lucas Beyer. *ICCV 2019*\n\n- 用于多模态语义分割的自监督模型适应。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1808.03833) \n  [[code]](https:\u002F\u002Fgithub.com\u002FDeepSceneSeg\u002FSSMA)\n  - Abhinav Valada, Rohit Mohan, 和 Wolfram Burgard. *IJCV 2019*\n\n#### 2020年\n - 自监督的批判性分析，或我们能从一张图片中学到什么\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1904.13132)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fyukimasano\u002Flinear-probes)\n   - Yuki M. Asano, Christian Rupprecht, Andrea Vedaldi. *ICLR 2020*\n\n - 关于表示学习中的互信息最大化\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1907.13625.pdf)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fgoogle-research\u002Ftree\u002Fmaster\u002Fmutual_information_representation_learning)\n   - Michael Tschannen, Josip Djolonga, Paul K. Rubenstein, Sylvain Gelly, Mario Lucic. *ICLR 2020*\n\n - 理解变分互信息估计器的局限性\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.06222)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fermongroup\u002Fsmile-mi-estimator)\n   - Jiaming Song, Stefano Ermon. *ICLR 2020*\n\n - 通过同时聚类和表示学习进行自标注\n   [[pdf]](https:\u002F\u002Fopenreview.net\u002Fpdf?id=Hyx-jyBFPr)\n   [[blogpost]](http:\u002F\u002Fwww.robots.ox.ac.uk\u002F~vgg\u002Fblog\u002Fself-labelling-via-simultaneous-clustering-and-representation-learning.html)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fyukimasano\u002Fself-label)\n   - Yuki Markus Asano, Christian Rupprecht, Andrea Vedaldi. *ICLR 2020（亮点论文）*\n\n - 通过输入变换进行自监督标签增强\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.05872)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fhankook\u002FSLA)\n   - Hankook Lee, Sung Ju Hwang, Jinwoo Shin. *ICML 2020*\n\n - 自监督表示学习中自动去除捷径\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2002.08822.pdf)\n   - Matthias Minderer, Olivier Bachem, Neil Houlsby, Michael Tschannen\n\n - 视觉表征对比学习的简单框架\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.05709)\n    [[code]](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fsimclr)\n    - Ting Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey Hinton. *ICML 2020*\n\n - 自监督预训练对视觉任务有多大的用处？\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2003.14323)\n    [[code]](https:\u002F\u002Fgithub.com\u002Fprinceton-vl\u002Fselfstudy-render)\n    - Alejandro Newell, Jia Deng. *CVPR 2020*\n\n - 用于无监督视觉表征学习的动量对比\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1911.05722.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fmoco)\n    - Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, Ross Girshick. *CVPR 2020*\n\n- ClusterFit：提升视觉表征的泛化能力\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1912.03330)\n   - Xueting Yan*, Ishan Misra*, Abhinav Gupta, Deepti Ghadiyaram**, Dhruv Mahajan**. *CVPR 2020*\n\n- 前景不变的自监督表示学习\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1912.01991)\n   - Ishan Misra, Laurens van der Maaten. *CVPR 2020*\n\n- Bootstrap Your Own Latent：一种新的自监督学习方法\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.07733)\n    [[非官方代码]](https:\u002F\u002Fgithub.com\u002Flucidrains\u002Fbyol-pytorch)\n    - Jean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec, Pierre H. Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhaohan Daniel Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, Rémi Munos, Michal Valko. *NeurIPS 2020，口头报告*\n\n - 针对标注有限的医学图像分割的全局与局部特征对比学习\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.10511.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002Fkrishnabits001\u002Fdomain_specific_cl)\n    - Krishna Chaitanya, Ertunc Erdil, Neerav Karani, Ender Konukoglu。*NeurIPS 2020，口头报告*\n\n - 通过不变性传播进行无监督表示学习\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2010.11694.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002FWangFeng18\u002FInvariancePropagation)\n    - Feng Wang, Huaping Liu, Di Guo, Fuchun Sun。*NeurIPS 2020，亮点论文*\n\n - 大型自监督模型是强大的半监督学习者\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.10029)\n    [[code]](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fsimclr)\n    - Ting Chen, Simon Kornblith, Kevin Swersky, Mohammad Norouzi, Geoffrey Hinton。*NeurIPS 2020*\n\n - 用于少样本分类的自监督原型迁移学习\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.11325.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002Findy-lab\u002FProtoTransfer)\n    - Carlos Medina, Arnout Devos, Matthias Grossglauser\n\n - SCAN：无需标签即可学习图像分类\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.12320)\n    [[code]](https:\u002F\u002Fgithub.com\u002Fwvangansbeke\u002FUnsupervised-Classification)\n    - Wouter Van Gansbeke, Simon Vandenhende, Stamatios Georgoulis, Marc Proesmans, Luc Van Gool。*ECCV 2020*\n\n - 通过对比聚类分配进行视觉特征的无监督学习\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.09882)\n    [[code]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fswav)\n    - Mathilde Caron, Ishan Misra, Julien Mairal, Priya Goyal, Piotr Bojanowski, Armand Joulin。*NeurIPS 2020*\n\n - 用于表示学习的自监督关系推理\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.05849.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002Fmpatacchiola\u002Fself-supervised-relational-reasoning)\n    - Massimiliano Patacchiola, Amos Storkey。*NeurIPS 2020，亮点论文*\n\n - 探索简单的暹罗表示学习\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2011.10566)\n    [[非官方代码]](https:\u002F\u002Fgithub.com\u002FPatrickHua\u002FSimSiam)\n    - Xinlei Chen, Kaiming He\n\n - 用于无监督表示学习的在线视觉词袋生成\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2012.11552)\n    [[code]](https:\u002F\u002Fgithub.com\u002Fvaleoai\u002Fobow)\n    - Spyros Gidaris, Andrei Bursuc, Gilles Puy, Nikos Komodakis, Matthieu Cord, Patrick Pérez\n\n - 重新思考标签在改善类别不平衡学习中的价值\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.07529)\n    [[code]](https:\u002F\u002Fgithub.com\u002FYyzHarry\u002Fimbalanced-semi-self)\n    - Yuzhe Yang, Zhi Xu。*NeurIPS 2020*\n\n- 揭秘对比自监督学习：不变性、数据增强与数据集偏差\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2007.13916.pdf)\n    - Senthil Purushwalkam, Abhinav Gupta. *NeurIPS 2020*\n\n- 缓解无监督图像分类中的嵌入与类别分配不匹配问题\n    [[pdf]](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-030-58586-0_45)\n    [[code]](https:\u002F\u002Fgithub.com\u002FSungwon-Han\u002FTwoStageUC)\n    - Sungwon Han, Sungwon Park, Sungkyu Park, Sundong Kim, Meeyoung Cha. *ECCV 2020*\n\n#### 2021年\n - 跨领域自监督学习\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.12368)\n    - Silvia Bucci, Antonio D'Innocente, Yujun Liao, Fabio Maria Carlucci, Barbara Caputo, Tatiana Tommasi. *T-PAMI 2021*\n\n - Barlow Twins：通过冗余减少实现自监督学习\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2103.03230)\n  [[code]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fbarlowtwins) \n    - Zbontar, J., Jing, L., Misra, I., LeCun, Y., & Deny, S.\n\n - 对比半监督学习在二维医学图像分割中的应用\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.06801)\n   - Prashant Pandey, Ajey Pai, Nisarg Bhatt, Prasenjit Das, Govind Makharia, Prathosh AP, Mausam. *MICCAI 2021*\n   \n - 自我传播：探索像素级一致性用于无监督视觉表征学习\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2011.10043)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fzdaxie\u002FPixPro)\n   - Zhenda Xie, Yutong Lin, Zheng Zhang, Yue Cao, Stephen Lin, and Han Hu. *CVPR 2021*\n\n - 自监督模型的迁移能力如何？\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.13377)\n   [[code]](https:\u002F\u002Fgithub.com\u002Flinusericsson\u002Fssl-transfer)\n   - Linus Ericsson, Henry Gouk, Timothy M. Hospedales. *CVPR 2021*\n\n- 向量化与栅格化：草图与手写体的自监督学习。  \n  [[code]](https:\u002F\u002Fgithub.com\u002FAyanKumarBhunia\u002FSelf-Supervised-Learning-for-Sketch)\n  - Ayan Kumar Bhunia, Pinaki nath Chowdhury, Yongxin Yang, Timothy Hospedales, Tao Xiang, Yi-Zhe Song. *CVPR 2021*\n\n - SelfAugment：自监督学习的自动数据增强策略\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2009.07724)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fcjrd\u002Fselfaugment)\n   - Colorado Reed, Sean Metzger, Aravind Srinivas, Trevor Darrell, Kurt Keutzer. *CVPR 2021*\n \n - 拼图聚类用于无监督视觉表征学习\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.00323)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fdvlab-research\u002FJigsawClustering)\n   - Pengguang Chen, Shu Liu, Jiaya Jia. *CVPR 2021*\n   \n - 通过鲁棒学习改进无监督图像聚类\n   [[pdf]](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2021\u002Fpapers\u002FPark_Improving_Unsupervised_Image_Clustering_With_Robust_Learning_CVPR_2021_paper.pdf)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fdeu30303\u002FRUC)\n   - Sungwon Park, Sungwon Han, Sundong Kim, Danu Kim, Sungkyu Park, Seunghoon Hong, Meeyoung Cha. *CVPR 2021*\n\n - 通过可视化特征变换改进对比学习\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2108.02982)\n   [[code]](https:\u002F\u002Fgithub.com\u002FDTennant\u002FCL-Visualizing-Feature-Transformation)\n   - Rui Zhu*, Bingchen Zhao*, Jingen Liu, Zhenglong Sun, Chang Wen Chen. *ICCV 2021 口头报告*\n\n#### 2022年\n - 针对有监督学习定制自监督方法\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2207.10023)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fwjun0830\u002FLocalizable-Rotation)\n   - WonJun Moon, Ji-Hwan Kim, Jae-Pil Heo. *ECCV 2022*\n   \n - FedX：基于跨知识蒸馏的无监督联邦学习\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2207.09158)\n   [[code]](https:\u002F\u002Fgithub.com\u002FSungwon-Han\u002FFEDX)\n   - Sungwon Han, Sungwon Park, Fangzhao Wu, Sundong Kim, Chuhan Wu, Xing Xie, Meeyoung Cha. *ECCV 2022*\n  \n - 掩码暹罗网络用于标签高效学习\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2204.07141)\n   [[code]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fmsn)\n   - Mahmoud Assran, Mathilde Caron, Ishan Misra, Piotr Bojanowski, Florian Bordes, Pascal Vincent, Armand Joulin, Michael Rabbat, Nicolas Ballas。\n\n - TriBYOL：三元组BYOL用于自监督表征学习\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.03012)\n   - Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama. *ICASSP 2022*\n\n - 基于自我知识蒸馏的自监督学习用于胸部X光片中的COVID-19检测\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.03009)\n   - Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama. *ICASSP 2022*\n \n - 自适应软对比学习\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2207.11163)\n   [[code]](https:\u002F\u002Fgithub.com\u002FMrChenFeng\u002FASCL_ICPR2022)\n   - Chen Feng, Ioannis Patras. *ICPR 2022*\n   \n  - 基于语义分组的自监督视觉表征学习\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2205.15288) \n    [[code]](https:\u002F\u002Fgithub.com\u002FCVMI-Lab\u002FSlotCon)\n    - Xin Wen, Bingchen Zhao, Anlin Zheng, Xiangyu Zhang, and Xiaojuan Qi. *NeurIPS 2022*\n   \n - VICReg：自监督学习中的方差-不变性-协方差正则化\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2105.04906)\n   - Adrien Bardes, Jean Ponce, Yann LeCun. *ICLR 2022*  \n\n#### 2023年\n - 对于对比学习的实例间相似性建模\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.12243) \n   [[code]](https:\u002F\u002Fgithub.com\u002Fvisresearch\u002Fpatchmix)\n   - Chengchao Shen, Dawei Liu, Hao Tang, Zhe Qu, Jianxin Wang。\n - 对于对比学习的非对称补丁采样\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.02854)\n   [[code]](https:\u002F\u002Fgithub.com\u002Fvisresearch\u002Faps)\n   - Chengchao Shen, Jianzhong Chen, Shu Wang, Hulin Kuang, Jin Liu, Jianxin Wang。\n\n#### 2024年\n - 通过对比自监督学习推动深度神经网络进化\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2406.14525) \n   [[code]](https:\u002F\u002Fgithub.com\u002Fcdvetal\u002Fevodenss)\n   - Adriano Vinhas, João Correia, Penousal Machado. *CEC 2024*\n\n\n\n### 视频表征学习\n\n- 使用LSTM进行视频表征的无监督学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1502.04681.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Femansim\u002Funsupervised-videos)\n  - Srivastava, Nitish 和 Mansimov, Elman 以及 Salakhudinov, Ruslan。 *ICML 2015*\n\n- 打乱并学习：利用时间顺序验证进行无监督学习。\n  [[pdf]](http:\u002F\u002Farxiv.org\u002Fabs\u002F1603.08561) \n  [[code]](https:\u002F\u002Fgithub.com\u002Fimisra\u002Fshuffle-tuple)\n  - Ishan Misra、C. Lawrence Zitnick 和 Martial Hebert。 *ECCV 2016*\n  \n- LSTM自监督用于详细行为分析\n  [[pdf]](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2017\u002Fpapers\u002FBrattoli_LSTM_Self-Supervision_for_CVPR_2017_paper.pdf)\n  - Biagio Brattoli*、Uta Büchler*、Anna-Sophia Wahl、Martin E. Schwab 和 Björn Ommer。 *CVPR 2017*\n  \n- 带有“异类”网络的自监督视频表征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1611.06646) \n  - Basura Fernando、Hakan Bilen、Efstratios Gavves 和 Stephen Gould。 *CVPR 2017*\n\n- 视频中长期运动动态的无监督学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1701.01821.pdf)\n  - 罗泽伦、彭博雅、黄德安、阿拉希·亚历山大、李飞飞。*CVPR 2017*\n\n- 基于几何引导的卷积神经网络用于自监督视频表征学习。\n  [[pdf]](http:\u002F\u002Fai.ucsd.edu\u002F~haosu\u002Fpapers\u002Fcvpr18_geometry_predictive_learning.pdf) \n  - 甘创、龚博清、刘坤、苏浩、莱昂尼达斯·J·吉巴斯。*CVPR 2018*\n\n- 通过深度强化学习提升时空自监督。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1807.11293)\n  - 比阿吉奥·布拉托利*、乌塔·比克勒*、比约恩·奥默。*ECCV 2018*\n\n- 从视频中自监督学习人脸属性嵌入。\n  [[pdf]](http:\u002F\u002Fwww.robots.ox.ac.uk\u002F~vgg\u002Fpublications\u002F2018\u002FWiles18a\u002Fwiles18a.pdf)\n  - 怀尔斯、科普克、齐瑟曼。*BMVC 2018*\n\n- 利用时空立方拼图进行自监督视频表征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1811.09795.pdf)\n  - 金大勋、曹东贤、柳东根、权仁洙。*AAAI 2019*\n\n- 通过预测运动和外观统计量进行视频的自监督时空表征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1904.03597)\n  - 王江流、焦建波、鲍林超、何圣峰、刘云辉、刘伟。*CVPR 2019*\n\n- DynamoNet：动态动作与运动网络。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1904.11407.pdf)\n  - 阿里·迪巴、维韦克·夏尔马、卢克·范古尔、赖纳·施蒂费尔哈根。*ICCV 2019*\n\n- 从时间循环一致性中学习对应关系。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1903.07593) \n  [[code]](https:\u002F\u002Fgithub.com\u002Fxiaolonw\u002FTimeCycle)\n  - 王晓龙*、艾伦·贾布里*、阿列克谢·A·埃夫罗斯。*CVPR 2019*\n\n- 用于时序对应关系的联合任务自监督学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.11895) \n  [[code]](https:\u002F\u002Fgithub.com\u002FLiusifei\u002FUVC)\n  - 李雪婷*、刘思菲*、沙莉妮·德梅洛、王晓龙、扬·考茨、杨明轩。*NIPS 2019*\n\n- 使用跨内对比框架进行自监督视频表征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2008.02531.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002FBestJuly\u002FIIC)\n  - 李涛、王雪婷*、山崎俊彦。*ACMMM 2020*\n\n- 自监督时空表征学习中的视频播放速率感知。\n  [[pdf]](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_CVPR_2020\u002Fpapers\u002FYao_Video_Playback_Rate_Perception_for_Self-Supervised_Spatio-Temporal_Representation_Learning_CVPR_2020_paper.pdf)\n  [[Code]](https:\u002F\u002Fgithub.com\u002Fyuanyao366\u002FPRP)\n  - 袁瑶*、刘畅*、罗德昭、周宇、叶启翔。*CVPR 2020*\n\n- 通过节奏预测进行自监督视频表征学习。\n  [[pdf]](http:\u002F\u002Fwww.robots.ox.ac.uk\u002F~vgg\u002Fpublications\u002F2020\u002FWang20\u002Fwang20.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Flaura-wang\u002Fvideo-pace)\n  - 王江流、焦建波、刘云辉。*ECCV 2020*\n\n- 通过识别时间变换进行视频表征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2007.10730.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fsjenni\u002Ftemporal-ssl)\n  - 西蒙·詹尼、吉维·梅什维利、保罗·法瓦罗。*ECCV 2020*\n\n- 用于视频表征学习的自监督协同训练。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2010.09709)\n  [[code]](https:\u002F\u002Fgithub.com\u002FTengdaHan\u002FCoCLR)\n  - 韩腾达、谢卫地、安德鲁·齐瑟曼。*NeurIPS 2020*\n\n- 用于自监督视频表征学习的循环对比。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2010.14810)\n  - 孔泉、魏文鹏、邓子威、吉永智明、村上友一。*NeurIPS 2020*\n\n- 基于视觉节奏一致性的视频表征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.15489)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fdecisionforce\u002FVTHCL)\n  - 杨策源、许英浩、戴博、周伯礼。\n\n- 通过揭示时空统计信息进行自监督视频表征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2008.13426)\n  - 王江流、焦建波、鲍林超、何圣峰、刘伟、刘云辉。\n\n- 时空对比视频表征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2008.03800)\n  - 钱瑞、孟天健、龚博清、杨明轩、王慧生、塞尔日·贝隆吉、崔音。\n\n- 基于预文本对比学习的自监督视频表征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2010.15464)\n  - 李涛、王雪婷、山崎俊彦。\n\n- 通过双向特征预测进行无监督视频表征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2011.06037)\n  - 纳丁·贝尔曼、尤尔根·加尔、梅赫迪·诺鲁齐。\n\n- RSPNet：用于无监督视频表征学习的相对速度感知。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2011.07949)\n  [[code]](https:\u002F\u002Fgithub.com\u002FPeihaoChen\u002FRSPNet)\n  - 陈培豪、黄登亮、何东梁、龙翔、曾润浩、温世磊、谭明奎、甘创。*AAAI 2021*\n\n- 分层解耦的空间-时间对比用于自监督视频表征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2011.11261)\n  - 张哲华、大卫·克兰达尔。\n\n- 时间信息能否帮助对比式自监督学习？\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2011.13046)\n  - 白宇彤、范浩奇、米斯拉·伊桑、文卡特什·加内什、陆勇毅、周雨茵、余启航、钱立克·维卡斯、艾伦·尤伊尔。\n\n- 通过解耦场景与运动来增强无监督视频表征学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2009.05757)\n  [[code]](https:\u002F\u002Fgithub.com\u002FFingerRec\u002FDSM-decoupling-scene-motion)\n  - 王金鹏、高玉婷、李可、胡建国、蒋新阳、郭晓伟、季荣荣、孙星。*AAAI 2021*\n\n- 时空对应作为对比随机游走。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.14613)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fajabri\u002Fvideowalk\u002F)\n  [[project]](http:\u002F\u002Fajabri.github.io\u002Fvideowalk)\n  - 艾伦·贾布里、安德鲁·欧文斯、阿列克谢·A·埃夫罗斯。*NeurIPS 2020 口头报告*\n\n#### 视频自监督学习的基准代码\n- 视频自监督学习中的基准敏感性有多严重？\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2203.14221) \n  [[code]](https:\u002F\u002Fgithub.com\u002Ffmthoker\u002FSEVERE-BENCHMARK)\n  - 托克尔、菲达·穆罕默德、多蒂、巴加德、斯诺克。*ECCV 2022*\n\n### 3D特征学习\n- 通过重构空间实现点云的自监督深度学习\n  [[pdf]](http:\u002F\u002Fpapers.neurips.cc\u002Fpaper\u002F9455-self-supervised-deep-learning-on-point-clouds-by-reconstructing-space.pdf)\n  - Jonathan Sauder, 和 Bjarne Sievers *NeurIPS 2019*\n\n- 基于姿态估计的点云自监督学习\n  [[pdf]](http:\u002F\u002Fwww.vovakim.com\u002Fpapers\u002F20_3DV_RotationSupervision.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002FOmidPoursaeed\u002FSelf_supervised_Learning_Point_Clouds)\n  - Omid Poursaeed, Tianxing Jiang, Han Qiao, Nayun Xu, 和 Vladimir G. Kim,*3DV 2020* \n\n- 通过学习离散生成模型实现3D点云的自监督学习\n  [[pdf]](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2021\u002Fpapers\u002FEckart_Self-Supervised_Learning_on_3D_Point_Clouds_by_Learning_Discrete_Generative_CVPR_2021_paper.pdf) \n  - Benjamin Eckart, Wentao Yuan, Chao Liu, 和 Jan Kautz *CVPR 2021*\n\n- PointContrast：面向3D点云的无监督预训练\n  [[pdf]](https:\u002F\u002Fwww.ecva.net\u002Fpapers\u002Feccv_2020\u002Fpapers_ECCV\u002Fpapers\u002F123480579.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002FPointContrast)\n  - Saining Xie, Jiatao Gu, Demi Guo, Charles R. Qi, Leonidas Guibas, 和 Or Litany *ECCV 2020*\n\n- 半监督点云语义分割的引导式点对比学习\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2110.08188)\n  - Li Jiang, Shaoshuai Shi, Zhuotao Tian, Xin Lai, Shu Liu, Chi-Wing Fu, 和 Jiaya Jia *ICCV 2021*\n\n- Ponder：基于神经渲染的点云预训练\n  [[pdf]](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FICCV2023\u002Fhtml\u002FHuang_Ponder_Point_Cloud_Pre-training_via_Neural_Rendering_ICCV_2023_paper.html)\n  - Di Huang, Sida Peng, Tong He, Honghui Yang, Xiaowei Zhou 和 Wanli Ouyang *ICCV 2023*\n\n- PonderV2：以通用预训练范式为3D基础模型铺路\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.08586)\n  [[code]](https:\u002F\u002Fgithub.com\u002FOpenGVLab\u002FPonderV2)\n  - Haoyi Zhu, Honghui Yang, Xiaoyang Wu, Di Huang, Tong He, Hengshuang Zhao, Chunhua Shen, Yu Qiao 和 Wanli Ouyang *Arxiv 2023*\n\n- UniPAD：面向自动驾驶的通用预训练范式\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.08586)\n  [[code]]([https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.08370](https:\u002F\u002Fgithub.com\u002FNightmare-n\u002FUniPAD))\n  - Honghui Yang, Sha Zhang, Di Huang, Xiaoyang Wu, Haoyi Zhu, Tong He, Shixiang Tang, Hengshuang Zhao, Qibo Qiu, Binbin Lin, Xiaofei He, 和 Wanli Ouyang *Arxiv 2023*\n\n### 几何\n- 用于单目深度估计的无监督CNN：几何来解救。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1603.04992.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002FRavi-Garg\u002FUnsupervised_Depth_Estimation)\n  - Ravi Garg, Vijay Kumar BG, Gustavo Carneiro, Ian Reid. *ECCV 2016*\n\n- 运动捕捉的自监督学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1712.01337.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fhtung0101\u002F3d_smpl)\n  [[web]](https:\u002F\u002Fsites.google.com\u002Fview\u002Fselfsupervisedlearningofmotion\u002F)\n  - Tung, Hsiao-Yu 和 Tung, Hsiao-Wei 以及 Yumer, Ersin 和 Fragkiadaki, Katerina. *NIPS 2017*\n\n- 通过密集等变图像标注进行对象帧的无监督学习。\n  [[pdf]](http:\u002F\u002Fpapers.neurips.cc\u002Fpaper\u002F6686-unsupervised-learning-of-object-frames-by-dense-equivariant-image-labelling.pdf)\n  - James Thewlis, Hakan Bilen, Andrea Vedaldi. *NeurIPS 2017*\n\n- 从视频中进行深度和自我运动的无监督学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1704.07813.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Ftinghuiz\u002FSfMLearner)\n  [[web]](https:\u002F\u002Fpeople.eecs.berkeley.edu\u002F~tinghuiz\u002Fprojects\u002FSfMLearner\u002F)\n  - Zhou, Tinghui 和 Brown, Matthew 和 Snavely, Noah 和 Lowe, David G. *CVPR 2017*\n\n- 主动立体网络：面向主动立体系统的端到端自监督学习。\n  [[project]](http:\u002F\u002Fasn.cs.princeton.edu\u002F)\n  - Yinda Zhang*, Sean Fanello, Sameh Khamis, Christoph Rhemann, Julien Valentin, Adarsh Kowdle, Vladimir Tankovich, Shahram Izadi, Thomas Funkhouser. *ECCV 2018*\n\n- 面向城市场景理解的自监督相对深度学习。\n  [[pdf]](https:\u002F\u002Fpeople.cs.umass.edu\u002F~hzjiang\u002Ffiles\u002Fssr_depth.pdf)\n  [[project]](https:\u002F\u002Fpeople.cs.umass.edu\u002F~hzjiang\u002Fprojects\u002Fssr_depth\u002F)\n  - Huaizu Jiang*, Erik Learned-Miller, Gustav Larsson, Michael Maire, Greg Shakhnarovich. *ECCV 2018*\n\n- 面向相机定位的地图几何感知学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1712.03342)\n  [[code]](https:\u002F\u002Fgithub.com\u002FNVlabs\u002Fgeomapnet)\n  - Samarth Brahmbhatt, Jinwei Gu, Kihwan Kim, James Hays, 和 Jan Kautz. CVPR 2018\n\n- 通过概率内省实现几何稳定的特征自监督学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1804.01552)\n  [[web]](http:\u002F\u002Fwww.robots.ox.ac.uk\u002F~vgg\u002Fresearch\u002Fprobabilistic_introspection\u002F)\n  - David Novotny, Samuel Albanie, Diane Larlus, Andrea Vedaldi. CVPR 2018\n\n- 利用多视角几何进行3D人体姿态的自监督学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1903.02330)\n  - Muhammed Kocabas; Salih Karagoz; Emre Akbas. CVPR 2019\n\n- SelFlow：光流的自监督学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1904.09117)\n  - Jiangliu Wang; Jianbo Jiao; Linchao Bao; Shengfeng He; Yunhui Liu; Wei Liu. CVPR 2019\n\n- 通过描述子向量交换进行地标点的无监督学习。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.06427)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fjamt9000\u002FDVE)\n  [[web]](http:\u002F\u002Fwww.robots.ox.ac.uk\u002F~vgg\u002Fresearch\u002FDVE\u002F)\n  - James Thewlis, Samuel Albanie, Hakan Bilen, Andrea Vedaldi. ICCV 2019\n\n### 音频\n- 基于自监督多模态特征的视听场景分析。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1804.03641.pdf)\n  [[代码]](https:\u002F\u002Fgithub.com\u002Fandrewowens\u002Fmultisensory)\n  - 安德鲁·欧文斯、阿列克谢·A·埃夫罗斯。*ECCV 2018*\n\n- 会发声的物体。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1712.06651.pdf)\n  - R. Arandjelović, A. Zisserman。*ECCV 2018*\n\n- 通过观看无标签视频学习分离物体声音。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1804.01665)\n  [[项目]](http:\u002F\u002Fvision.cs.utexas.edu\u002Fprojects\u002Fseparating_object_sounds\u002F)\n  - 高若涵、罗杰里奥·费里斯、克里斯汀·格劳曼。*ECCV 2018*\n\n- 像素之声。\n  [[pdf]]( https:\u002F\u002Farxiv.org\u002Fpdf\u002F1804.03160.pdf )\n  [[项目]](https:\u002F\u002Fgithub.com\u002Fhangzhaomit\u002FSound-of-Pixels)\n  - 赵航、甘闯、安德鲁·鲁迪琴科、卡尔·冯德里克、乔什·麦克德莫特、安东尼奥·托拉尔巴。*ECCV 2018*\n\n- 可学习的PIN码：用于人员身份识别的跨模态嵌入。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1805.00833)\n  [[网页]](http:\u002F\u002Fwww.robots.ox.ac.uk\u002F~vgg\u002Fresearch\u002FLearnablePins\u002F)\n  - 阿尔沙·纳格拉尼、塞缪尔·阿尔巴尼、安德鲁·齐瑟曼。ECCV 2018\n\n- 基于自监督同步的音频与视频模型协同学习。\n  [[pdf]](http:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F8002-cooperative-learning-of-audio-and-video-models-from-self-supervised-synchronization.pdf)\n  - 布鲁诺·科尔巴尔，达特茅斯学院；杜·陈；洛伦佐·托雷萨尼。*NIPS 2018*\n\n- 360°视频的空间音频自监督生成。\n  [[pdf]](http:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F7319-self-supervised-generation-of-spatial-audio-for-360-video.pdf)\n  - 佩德罗·莫尔加多、努诺·纳瓦斯孔塞洛斯、蒂莫西·朗格卢瓦、奥利弗·王。*NIPS 2018*\n\n- 三循环：利用自监督从传感器网络数据中学习音频表示\n  [[pdf]](http:\u002F\u002Fwww.justinsalamon.com\u002Fuploads\u002F4\u002F3\u002F9\u002F4\u002F4394963\u002Fcartwright_tricycle_waspaa2019.pdf)\n  - 马克·卡特赖特、杰森·克雷默、贾斯汀·萨拉蒙、胡安·巴勃罗·贝略。*WASPAA 2019*\n\n- 自监督的视听共同分割\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1904.09013.pdf)\n  - 安德鲁·鲁迪琴科、赵航、甘闯、乔什·麦克德莫特和安东尼奥·托拉尔巴。*ICASSP 2019*\n\n- 视觉自监督能否提升语音表示的学习效果？\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2005.01400.pdf)\n   - 阿比纳夫·舒克拉、斯塔夫罗斯·佩特里迪斯、玛雅·潘蒂奇\n\n- 眼见未必为实：通过蒸馏多模态知识实现基于声音的自监督多目标检测与跟踪\n  [[pdf]](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent\u002FCVPR2021\u002Fpapers\u002FValverde_There_Is_More_Than_Meets_the_Eye_Self-Supervised_Multi-Object_Detection_CVPR_2021_paper.pdf) \n  [[代码]](https:\u002F\u002Fgithub.com\u002Frobot-learning-freiburg\u002FMM-DistillNet)\n\t- 弗朗西斯科·里韦拉·巴尔韦德、胡安娜·瓦莱丽亚·乌尔塔多和阿比纳夫·瓦拉达。*CVPR 2021*\n\n- BYOL for Audio：面向通用音频表示的自监督学习。\n [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2103.06695.pdf) \n [[代码]](https:\u002F\u002Fgithub.com\u002Fnttcslab\u002Fbyol-a)\n  - 新住大介、竹内大辉、大石康则 *IJCNN 2021*\n\n- 从可听交互中学习状态感知的视觉表示\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.13583)\n  [[代码]](https:\u002F\u002Fgithub.com\u002FHimangiM\u002FRepLAI)\n  - 希曼吉·米塔尔、佩德罗·莫尔加多、乌纳特·贾因、阿比纳夫·古普塔。*NeurIPS 2022*\n\n### 其他\n- 基于70万个人日可穿戴数据的自监督人体活动识别  \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2206.02909)  \n  [[代码]](https:\u002F\u002Fgithub.com\u002FOxWearables\u002Fssl-wearables)  \n  - Hang Yuan*, Shing Chan*, Andrew P. Creagh, Catherine Tong, David A. Clifton, Aiden Doherty\n  \n- 使用渐进式潜在模型的场景特定行人检测器自学习  \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1611.07544)  \n  - Qixiang Ye, Tianliang Zhang, Qiang Qiu, Baochang Zhang, Jie Chen, Guillermo Sapiro。*CVPR 2017*\n  \n- 来自电子游戏的无监督信号  \n  [[pdf]](http:\u002F\u002Fwww.philkr.net\u002Fpapers\u002F2018-06-01-cvpr\u002F2018-06-01-cvpr.pdf)  \n  [[项目+代码]](http:\u002F\u002Fwww.philkr.net\u002Ffsv\u002F)  \n  - Philipp Krähenbühl。*CVPR 2018*\n  \n- 打击假新闻：基于学习到的自一致性进行图像拼接检测  \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1805.04096.pdf)  \n  [[代码]](https:\u002F\u002Fgithub.com\u002Fminyoungg\u002Fselfconsistency)  \n  - Minyoung Huh*, Andrew Liu*, Andrew Owens, Alexei A. Efros。*ECCV 2018*\n  \n- 通过上色实现自监督跟踪（视频上色催生跟踪能力）  \n  [[pdf]](https:\u002F\u002Fwww.cs.columbia.edu\u002F~vondrick\u002F\u002Fvideocolor.pdf)  \n  - Carl Vondrick*, Abhinav Shrivastava, Alireza Fathi, Sergio Guadarrama, Kevin Murphy。*ECCV 2018*\n  \n- 更少标注下的高保真图像生成  \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.02271.pdf)  \n  - Mario Lucic*, Michael Tschannen*, Marvin Ritter*, Xiaohua Zhai, Olivier Bachem, Sylvain Gelly。\n  \n- 自监督将关节网格拟合到点云  \n  - Chun-Liang Li, Tomas Simon, Jason Saragih, Barnabás Póczos 和 Yaser Sheikh。*CVPR 2019*\n  \n- 随流而行：自监督场景光流估计  \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1912.00497.pdf)  \n  [[代码]](https:\u002F\u002Fgithub.com\u002FHimangiM\u002FJust-Go-with-the-Flow-Self-Supervised-Scene-Flow-Estimation)  \n  - Himangi Mittal、Brian Okorn、David Held。*CVPR 2020*\n  \n- SCOPS：自监督协同部件分割  \n  - Wei-Chih Hung、Varun Jampani、Sifei Liu、Pavlo Molchanov、Ming-Hsuan Yang 和 Jan Kautz。*CVPR 2019*\n  \n- 自监督高保真人脸模型适配用于单目动作捕捉  \n  - Jae Shin Yoon；Takaaki Shiratori；Shouou-I Yu；Hyun Soo Park。*CVPR 2019*\n  \n- 通过回收边界框标注实现多任务自监督目标检测  \n  [[pdf]](https:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_CVPR_2019\u002Fpapers\u002FLee_Multi-Task_Self-Supervised_Object_Detection_via_Recycling_of_Bounding_Box_Annotations_CVPR_2019_paper.pdf)  \n  [[代码]](https:\u002F\u002Fgithub.com\u002FwonheeML\u002Fmtl-ssl)  \n  - Wonhee Lee；Joonil Na；Gunhee Kim。*CVPR 2019*\n  \n- 自监督卷积子空间聚类网络  \n  - Junjian Zhang；Chun-Guang Li；Chong You；Xianbiao Qi；Honggang Zhang；Jun Guo；Zhouchen Lin。*CVPR 2019*\n  \n- 强化跨模态匹配与自监督模仿学习用于视觉-语言导航  \n  - Xin Wang；Qiuyuan Huang；Asli Celikyilmaz；Jianfeng Gao；Dinghan Shen；Yuan-Fang Wang；William Yang Wang；Lei Zhang。*CVPR 2019*\n  \n- 基于几何自监督的无监督3D姿态估计  \n  - Ching-Hang Chen；Ambrish Tyagi；Amit Agrawal；Dylan Drover；Rohith MV；Stefan Stojanov；James M. Rehg。*CVPR 2019*\n  \n- 在无需定位监督的情况下学习生成有语义关联的图像描述[[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1906.00283.pdf)  \n  - Chih-Yao Ma；Yannis Kalantidis；Ghassan AlRegib；Peter Vajda；Marcus Rohrbach；Zsolt Kira。\n- VideoBERT：视频与语言联合表示学习模型[[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1904.01766.pdf)  \n  - Chen Sun，Austin Myers，Carl Vondrick，Kevin Murphy，Cordelia Schmid。*ICCV 2019*\n  \n- 通过学习辅助干净标签来对抗噪声标签[[pdf]]( https:\u002F\u002Farxiv.org\u002Fpdf\u002F1905.13305.pdf )\n  - Tsung Wei Tsai，Chongxuan Li，Jun Zhu\n\n- 基于修复的自监督点云补全  \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2111.10701)  \n  - Himangi Mittal、Brian Okorn、Arpit Jangid、David Held。*BMVC 2021*\n  \n- ColloSSL：用于人体活动识别的协作式自监督学习  \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2202.00758.pdf)  \n  [[代码]](https:\u002F\u002Fgithub.com\u002Fakhilmathurs\u002Fcollossl)  \n  - Yash Jain、Ian Tang、Chulhong Min、Fahim Kawsar、Akhil Mathur。*UbiComp 2022*\n  \n## 机器学习\n- 自学式学习：从无标签数据中迁移学习  \n  [[pdf]](https:\u002F\u002Fai.stanford.edu\u002F~hllee\u002Ficml07-selftaughtlearning.pdf)  \n  - Raina、Rajat、Battle、Alexis、Lee、Honglak、Packer、Benjamin 和 Ng、Andrew Y。*ICML 2007*\n\n- 表征学习：综述与新视角  \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1206.5538.pdf)  \n  - Bengio、Yoshua、Courville、Aaron 和 Vincent、Pascal。*TPAMI 2013*。\n\n### 强化学习\n- 基于自监督预测的 curiosity-driven 探索  \n  [[pdf]](http:\u002F\u002Fpathak22.github.io\u002Fnoreward-rl\u002Fresources\u002Ficml17.pdf)  \n  [[代码]](https:\u002F\u002Fpathak22.github.io\u002Fnoreward-rl\u002Findex.html#sourceCode)  \n  - Deepak Pathak、Pulkit Agrawal、Alexei A. Efros 和 Trevor Darrell。*ICML 2017*\n\n- 大规模好奇心驱动学习研究  \n  [[pdf]](https:\u002F\u002Fpathak22.github.io\u002Flarge-scale-curiosity\u002Fresources\u002FlargeScaleCuriosity2018.pdf)  \n  - Yuri Burda*、Harri Edwards*、Deepak Pathak*、Amos Storkey、Trevor Darrell 和 Alexei A. Efros\n\n- 通过观看YouTube玩硬探索游戏  \n  [[pdf]](https:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F7557-playing-hard-exploration-games-by-watching-youtube.pdf)  \n  - Yusuf Aytar、Tobias Pfaff、David Budden、Tom Le Paine、Ziyu Wang、Nando de Freitas。*NIPS 2018*\n  \n- Atari游戏中的无监督状态表征学习  \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1906.08226.pdf)  \n  [[代码]](https:\u002F\u002Fgithub.com\u002Fmila-iqia\u002Fatari-representation-learning)  \n  - Ankesh Anand、Evan Racah、Sherjil Ozair、Yoshua Bengio、Marc-Alexandre Côté、R Devon Hjelm。*NeurIPS 2019*\n\n- 带有自监督3D表征的视觉强化学习  \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2210.07241.pdf)  \n  [[代码]](https:\u002F\u002Fgithub.com\u002FYanjieZe\u002Frl3d)  \n  - Yanjie Ze*、Nicklas Hansen*、Yinbo Chen、Mohit Jain、Xiaolong Wang。*预印本2022年*\n\n### 推荐系统\n- 推荐系统中深度模型的自监督学习  \n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2007.12865.pdf)  \n  - Tiansheng Yao、Xinyang Yi、Derek Zhiyuan Cheng、Felix Yu、Aditya Menon、Lichan Hong、Ed H. Chi、Steve Tjoa、Jieqi (Jay)Kang、Evan Ettinger *预印本2020年*\n\n\n## 机器人学\n\n### 2006年\n- 通过自监督在线学习改进机器人导航  \n  [[pdf]](http:\u002F\u002Fwww.roboticsproceedings.org\u002Frss02\u002Fp04.pdf)  \n  - Boris Sofman、Ellie Lin、J. Andrew Bagnell、Nicolas Vandapel 和 Anthony Stentz\n  \n- 反向光流用于自监督自适应自主机器人导航  \n  [[pdf]](https:\u002F\u002Fwww.cs.ait.ac.th\u002F~mdailey\u002Fcvreadings\u002FLookingbill-ReverseOptical.pdf)  \n  - A. Lookingbill、D. Lieb、J. Rogers 和 J. Curry\n\n### 2009年\n- 自主越野驾驶中的长距离视觉学习\n  [[pdf]](http:\u002F\u002Fyann.lecun.com\u002Fexdb\u002Fpublis\u002Fpdf\u002Fhadsell-jfr-09.pdf)\n  - Raia Hadsell、Pierre Sermanet、Jan Ben、Ayse Erkan、Marco Scoffier、Koray Kavukcuoglu、Urs Muller、Yann LeCun\n\n### 2012年\n- 用于行星表面探测漫游车的自监督地形分类\n  [[pdf]](https:\u002F\u002Fpdfs.semanticscholar.org\u002F66b7\u002Feef326d1db1fa2b19d5dc6b84d3d2a95b76c.pdf)\n  - Christopher A. Brooks、Karl Iagnemma\n\n### 2014年\n- 基于多传感器数据关联的移动机器人地形可通行性分析\n  [[pdf]](http:\u002F\u002Fsensor.eng.shizuoka.ac.jp\u002Fpdf\u002F2014\u002FSII.pdf)\n  - Mohammed Abdessamad Bekhti、Yuichi Kobayashi 和 Kazuki Matsumura\n\n### 2015年\n- 动态目标分割的在线自监督学习\n  [[pdf]](http:\u002F\u002Fciteseerx.ist.psu.edu\u002Fviewdoc\u002Fdownload?doi=10.1.1.875.5829&rep=rep1&type=pdf)\n  - Vitor Guizilini 和 Fabio Ramos，《国际机器人研究杂志》\n\n- 基本物体推动 affordance 的自监督在线学习\n  [[pdf]](http:\u002F\u002Fabr.ijs.si\u002Fpdf\u002F1429861734-RidgeIJARS2015.pdf)\n  - Barry Ridge、Ales Leonardis、Ales Ude、Miha Denisa 和 Danijel Skocaj\n\n- iCub 类人机器人上基于抓取的工具 affordance 的自监督学习\n  [[pdf]](https:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?tp=&arnumber=7139640)\n  - Tanis Mar、Vadim Tikhanoff、Giorgio Metta 和 Lorenzo Natale\n\n### 2016年\n- 持续自监督学习原理：从立体视觉到单目视觉的障碍物避让\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1603.08047.pdf)\n  - Kevin van Hecke、Guido de Croon、Laurens van der Maaten、Daniel Hennes 和 Dario Izzo\n\n- 好奇的机器人：通过物理交互学习视觉表征\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1604.01360v2)\n  - Lerrel Pinto、Dhiraj Gandhi、Yuanfeng Han、Yong-Lae Park 和 Abhinav Gupta。*ECCV 2016*\n\n- 通过戳刺来学习：直观物理的体验式学习\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1606.07419)\n  - Agrawal、Pulkit 和 Nair、Ashvin V、Abbeel、Pieter 和 Malik、Jitendra 和 Levine、Sergey。*NIPS 2016*\n\n- 扩大自监督规模：从 5 万次尝试和 700 小时机器人操作中学习抓取\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1509.06825.pdf)\n  - Pinto、Lerrel 和 Gupta、Abhinav。*ICRA 2016*\n\n### 2017年\n- 竞争式监督：用于学习任务的机器人对手\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1610.01685.pdf)\n  - Pinto、Lerrel 和 Davidson、James 和 Gupta、Abhinav。*ICRA 2017*\n\n- 多视角自监督深度学习在亚马逊拣选挑战赛中的 6D 姿态估计\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1803.09956.pdf) \n  [[项目]](http:\u002F\u002Fapc.cs.princeton.edu\u002F)\n  - Andy Zeng、Kuan-Ting Yu、Shuran Song、Daniel Suo、Ed Walker Jr.、Alberto Rodriguez、Jianxiong Xiao。*ICRA 2017*\n\n- 结合自监督学习与模仿学习的基于视觉的绳索操作\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1703.02018) \n  [[项目]](https:\u002F\u002Fropemanipulation.github.io\u002F)\n  - Ashvin Nair*、Dian Chen*、Pulkit Agrawal*、Phillip Isola、Pieter Abbeel、Jitendra Malik、Sergey Levine。*ICRA 2017*\n\n- 在碰撞中学习飞行\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1704.05588)\n  - Dhiraj Gandhi、Lerrel Pinto、Abhinav Gupta *IROS 2017*\n\n- 自监督学习作为未来太空探索机器人的赋能技术：国际空间站上的单目距离学习实验\n  [[pdf]](http:\u002F\u002Fwww.esa.int\u002Fgsp\u002FACT\u002Fdoc\u002FAI\u002Fpub\u002FACT-RPR-AI-2017-ACTA-SSL.pdf)\n  - K. van Hecke、G. C. de Croon、D. Hennes、T. P. Setterfield、A. Saenz- Otero 和 D. Izzo\n\n- 用于模仿学习的无监督感知奖励\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1612.06699)\n  [[项目]](https:\u002F\u002Fsermanet.github.io\u002Frewards\u002F)\n  - Sermanet、Pierre 和 Xu、Kelvin 和 Levine、Sergey。*RSS 2017*\n\n- 带有时间跳跃连接的自监督视觉规划\n  [[pdf]](http:\u002F\u002Farxiv.org\u002Fpdf\u002F1710.05268)\n  - Frederik Ebert、Chelsea Finn、Alex X. Lee、Sergey Levine。*CoRL2017*\n\n### 2018年\n- CASSL：课程加速的自监督学习\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1708.01354.pdf) \n  - Adithyavairavan Murali、Lerrel Pinto、Dhiraj Gandhi、Abhinav Gupta。*ICRA 2018*\n\n- 时间对比网络：从视频中进行自监督学习\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1609.09475.pdf) \n  [[项目]](https:\u002F\u002Fsermanet.github.io\u002Fimitate\u002F)\n  - Pierre Sermanet、Corey Lynch、Yevgen Chebotar、Jasmine Hsu、Eric Jang、Stefan Schaal 和 Sergey Levine。*ICRA 2018*\n\n- 基于广义计算图的自监督深度强化学习用于机器人导航\n  [[pdf]](http:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.10489) \n  - Gregory Kahn、Adam Villaflor、Bosen Ding、Pieter Abbeel、Sergey Levine。*ICRA 2018*\n\n- 从视觉观测中学习可行动表征\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1609.09475.pdf) \n  [[项目]](https:\u002F\u002Fsermanet.github.io\u002Fimitate\u002F)\n  - Dwibedi、Debidatta 和 Tompson、Jonathan 以及 Lynch、Corey 和 Sermanet、Pierre。*IROS 2018*\n\n- 利用自监督深度强化学习学习推与抓之间的协同作用\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1808.00928) \n  [[项目]](https:\u002F\u002Fsites.google.com\u002Fview\u002Factionablerepresentations\u002F)\n  - Andy Zeng、Shuran Song、Stefan Welker、Johnny Lee、Alberto Rodriguez、Thomas Funkhouser。*IROS 2018*\n\n- 带有想象目标的视觉强化学习\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1807.04742) \n  [[项目]](https:\u002F\u002Fsites.google.com\u002Fsite\u002Fvisualrlwithimaginedgoals\u002F)\n  - Ashvin Nair*、Vitchyr Pong*、Murtaza Dalal、Shikhar Bahl、Steven Lin、Sergey Levine。*NeurIPS 2018*\n\n- Grasp2Vec：从自监督抓取中学习物体表征\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1811.06964.pdf) \n  [[项目]](https:\u002F\u002Fsites.google.com\u002Fsite\u002Fgrasp2vec\u002Fhome)\n  - Eric Jang*、Coline Devin*、Vincent Vanhoucke、Sergey Levine。*CoRL 2018*\n\n- 通过重试提升鲁棒性：基于自监督学习的闭环机器人操作\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1810.03043.pdf) \n  [[项目]](https:\u002F\u002Fsites.google.com\u002Fview\u002Frobustness-via-retrying)\n  - Frederik Ebert、Sudeep Dasari、Alex X. Lee、Sergey Levine、Chelsea Finn。*CoRL 2018*\n\n### 2019年\n- 利用短程传感器和里程计的自监督学习长距离感知\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1809.07207)\n  - Mirko Nava、Jerome Guzzi、R. Omar Chavez-Garcia、Luca M. Gambardella、Alessandro Giusti。*机器人与自动化快报*\n\n- 从玩耍中学习潜在计划\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1903.01973.pdf) \n  [[项目]](https:\u002F\u002Flearning-from-play.github.io\u002F)\n  - Corey Lynch、Mohi Khansari、Ted Xiao、Vikash Kumar、Jonathan Tompson、Sergey Levine、Pierre Sermanet\n\n- 从无监督声学特征学习中进行的自监督视觉地形分类\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1912.03227.pdf) \n  - Jannik Zuern、Wolfram Burgard、Abhinav Valada\n\n### 2020年\n- 对抗技能网络：从视频中无监督学习机器人技能。\n[[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.09430.pdf) \n  [[项目]](http:\u002F\u002Frobotskills.cs.uni-freiburg.de\u002F)\n  - Oier Mees、Markus Merklinger、Gabriel Kalweit、Wolfram Burgard *ICRA 2020*\n\n### 2023年\n- 基于原位微调的自监督目标导航。\n[[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2212.05923) \n[[视频]](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=LXsZst5ZUpU)\n  - So Yeon Min、Yao-Hung Hubert Tsai、Wei Ding、Ali Farhadi、Ruslan Salakhutdinov、Yonatan Bisk、Jian Zhang *IROS 2023*\n\n### 2024年\n- 点云的重要性：重新思考不同观测空间对机器人学习的影响。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2402.02500.pdf)\n  - Haoyi Zhu、Yating Wang、Di Huang、Weicai Ye、Wanli Ouyang、Tong He\n\n## 自然语言处理\n- BERT：用于语言理解的深度双向Transformer预训练。\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1810.04805)\n  [[链接]](https:\u002F\u002Fgithub.com\u002Fgoogle-research\u002Fbert)\n  - Jacob Devlin、Ming-Wei Chang、Kenton Lee、Kristina Toutanova。*NAACL 2019 最佳长文*\n\n- 自监督对话学习\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1907.00448.pdf)\n  - Jiawei Wu、Xin Wang、William Yang Wang。*ACL 2019*\n\n- 面向上下文化抽取式摘要的自监督学习\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1906.04466.pdf)\n  - Hong Wang、Xin Wang、Wenhan Xiong、Mo Yu、Xiaoxiao Guo、Shiyu Chang、William Yang Wang。*ACL 2019*\n\n- 语言表示学习的互信息最大化视角\n  [[pdf]](https:\u002F\u002Fopenreview.net\u002Fpdf?id=Syx79eBKwr)\n  - Lingpeng Kong、Cyprien de Masson d'Autume、Lei Yu、Wang Ling、Zihang Dai、Dani Yogatama。*ICLR 2020*\n\n- VL-BERT：通用视觉-语言表示的预训练\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1908.08530.pdf)\n  [[代码]](https:\u002F\u002Fgithub.com\u002Fjackroos\u002FVL-BERT)\n  - Weijie Su、Xizhou Zhu、Yue Cao、Bin Li、Lewei Lu、Furu Wei、Jifeng Dai。*ICLR 2020*\n\n- 一种简单有效的自监督对比学习框架，用于方面检测\n  [[pdf]](https:\u002F\u002Fpeople.cs.vt.edu\u002F~reddy\u002Fpapers\u002FAAAI21.pdf)\n  [[代码]](https:\u002F\u002Fgithub.com\u002Ftshi04\u002FAspDecSSCL)\n  - Tian Shi、Liuqing Li、Ping Wang 和 Chandan K. Reddy。*AAAI 2021*\n\n- BERT句子表示的自引导对比学习\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.07345)\n  [[代码]](https:\u002F\u002Fgithub.com\u002Fgalsang\u002FSG-BERT)\n  - Taeuk Kim、Kang Min Yoo 和 Sang-goo Lee。*ACL 2021*\n\n## 自动语音识别\n- wav2vec：用于语音识别的无监督预训练\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1904.05862.pdf)\n  [[代码]](https:\u002F\u002Fgithub.com\u002Fpytorch\u002Ffairseq\u002Ftree\u002Fmaster\u002Fexamples\u002Fwav2vec)\n  - Steffen Schneider、Alexei Baevski、Ronan Collobert、Michael Auli。*INTERSPEECH 2019*\n\n- 学习鲁棒且多语言的语音表示\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2001.11128.pdf)\n  - Kazuya Kawakami、Luyu Wang、Chris Dyer、Phil Blunsom、Aaron van den Oord。*EMNLP 2020 结果*\n\n- 无监督预训练在不同语言间具有良好的迁移性\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2002.02848.pdf)\n  [[代码]](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002FCPC_audio)\n  - Morgane Riviere、Armand Joulin、Pierre-Emmanuel Mazare、Emmanuel Dupoux。*ICASSP 2020*\n\n- vq-wav2vec：离散语音表示的自监督学习\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.05453)\n  - Alexei Baevski、Steffen Schneider、Michael Auli。*ICLR 2020*\n\n- 自监督预训练在语音识别中的有效性\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1911.03912.pdf)\n  - Alexei Baevski、Michael Auli、Abdelrahman Mohamed。*ICASSP 2020*\n\n- 基于量化语音表示学习的无监督语音识别与合成\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.12729)\n  - Alexander H. Liu、Tao Tu、Hung-yi Lee、Lin-shan Lee。*ICASSP 2020*\n\n- 面向端到端语音识别的自训练\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1909.09116)\n  - Jacob Kahn、Ann Lee、Awni Hannun。*ICASSP 2020*\n\n- 基于自回归预测编码的语音生成式预训练\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1910.12607.pdf)\n  [[代码]](https:\u002F\u002Fgithub.com\u002Fiamyuanchung\u002FAutoregressive-Predictive-Coding)\n  - Yu-An Chung、James Glass。*ICASSP 2020*\n\n- 利用跨模态自监督学习解耦语音嵌入\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2002.08742v1.pdf)\n  - Arsha Nagrani、Joon Son Chung、Samuel Albanie、Andrew Zisserman。*ICASSP 2020*\n\n- 面向鲁棒语音识别的多任务自监督学习\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2001.09239.pdf)\n  - Mirco Ravanelli、Jianyuan Zhong、Santiago Pascual、Pawel Swietojanski、Joao Monteiro、Jan Trmal、Yoshua Bengio。*ICASSP 2020*\n\n- 视觉引导的语音表示自监督学习\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2001.04316.pdf)\n  - Abhinav Shukla、Konstantinos Vougioukas、Pingchuan Ma、Stavros Petridis、Maja Pantic。*ICASSP 2020*\n\n- Mockingjay：基于深度双向Transformer编码器的无监督语音表示学习\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F1910.12638)\n  [[代码]](https:\u002F\u002Fgithub.com\u002Fs3prl\u002Fs3prl)\n  - Andy T. Liu、Shu-wen Yang、Po-Han Chi、Po-chun Hsu、Hung-yi Lee。*ICASSP 2020*\n\n- 向量量化自回归预测编码\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.08392)\n  [[代码]](https:\u002F\u002Fgithub.com\u002FAlexander-H-Liu\u002FNPC)\n  - Yu-An Chung、Hao Tang、James Glass。*Interspeech 2020*\n\n- wav2vec 2.0：语音表示自监督学习框架\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.11477)\n  [[代码]](https:\u002F\u002Fgithub.com\u002Fpytorch\u002Ffairseq\u002Ftree\u002Fmaster\u002Fexamples\u002Fwav2vec)\n  - Alexei Baevski、Yuhao Zhou、Abdelrahman Mohamed、Michael Auli。*NeurIPS 2020*\n\n- 鲁棒的wav2vec 2.0：分析自监督预训练中的领域偏移\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2104.01027)\n  [[代码]](https:\u002F\u002Fgithub.com\u002Fpytorch\u002Ffairseq\u002Ftree\u002Fmaster\u002Fexamples\u002Fwav2vec)\n  - Wei-Ning Hsu、Anuroop Sriram、Alexei Baevski、Tatiana Likhomanenko、Qiantong Xu、Vineel Pratap、Jacob Kahn、Ann Lee、Ronan Collobert、Gabriel Synnaeve、Michael Auli\n\n- HuBERT：通过掩码预测隐藏单元进行自监督语音表示学习\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.07447)\n  [[代码]](https:\u002F\u002Fgithub.com\u002Fpytorch\u002Ffairseq\u002Ftree\u002Fmaster\u002Fexamples\u002Fhubert)\n  - Wei-Ning Hsu、Benjamin Bolte、Yao-Hung Hubert Tsai、Kushal Lakhotia、Ruslan Salakhutdinov、Abdelrahman Mohamed。*ICASSP 2021*\n\n- 无监督语音识别\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2105.11084)\n  [[代码]](https:\u002F\u002Fgithub.com\u002Fpytorch\u002Ffairseq\u002Ftree\u002Fmaster\u002Fexamples\u002Fwav2vec\u002Funsupervised)\n  - Alexei Baevski、Wei-Ning Hsu、Alexis Conneau、Michael Auli\n\n- TERA：面向语音的Transformer编码器表示自监督学习\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2007.06028)\n  [[代码]](https:\u002F\u002Fgithub.com\u002Fs3prl\u002Fs3prl)\n  - Andy T. Liu、Shang-Wen Li、Hung-yi Lee。*IEEE\u002FACM TASLP 2021*\n\n- 非自回归预测编码：从局部依赖中学习语音表示\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fabs\u002F2011.00406)\n  [[代码]](https:\u002F\u002Fgithub.com\u002FAlexander-H-Liu\u002FNPC)\n  - Alexander H. Liu、Yu-An Chung、James Glass。*Interspeech 2021*\n\n## 时间序列\n- 多变量时间序列的无监督可扩展表示学习\n  [[pdf]](https:\u002F\u002Fproceedings.neurips.cc\u002Fpaper\u002F2019\u002Ffile\u002F53c6de78244e9f528eb3e1cda69699bb-Paper.pdf)\n  [[代码]](https:\u002F\u002Fgithub.com\u002FWhite-Link\u002FUnsupervisedScalableRepresentationLearningTimeSeries)\n  - Franceschi、Jean-Yves、Aymeric Dieuleveut 和 Martin Jaggi。*NeurIPS 2019*\n\n- 基于时间和上下文对比的时间序列表示学习\n  [[pdf]](https:\u002F\u002Fwww.ijcai.org\u002Fproceedings\u002F2021\u002F0324.pdf)\n  [[代码]](https:\u002F\u002Fgithub.com\u002Femadeldeen24\u002FTS-TCC)\n  - Emadeldeen Eldele、Mohamed Ragab、Zhenghua Chen、Min Wu、Chee Keong Kwoh、Xiaoli Li 和 Cuntai Guan。*IJCAI 2021*\n\n- 基于时间邻域编码的时间序列无监督表示学习\n  [[pdf]](https:\u002F\u002Fopenreview.net\u002Fpdf?id=8qDwejCuCN)\n  [[代码]](https:\u002F\u002Fgithub.com\u002Fsanatonek\u002FTNC_representation_learning)\n  - Tonekaboni、Sana、Danny Eytan 和 Anna Goldenberg。*ICLR 2021*\n\n- 基于Transformer的多变量时间序列表示学习框架\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2010.02803.pdf)\n  [[代码]](https:\u002F\u002Fgithub.com\u002Fgzerveas\u002Fmvts_transformer)\n  - Zerveas、George、Srideepika Jayaraman、Dhaval Patel、Anuradha Bhamidipaty 和 Carsten Eickhoff。*KDD 2021*\n\n- TS2Vec：迈向时间序列的通用表示\n  [[pdf]](https:\u002F\u002Fwww.aaai.org\u002FAAAI22Papers\u002FAAAI-8809.YueZ.pdf)\n  [[代码]](https:\u002F\u002Fgithub.com\u002Fyuezhihan\u002Fts2vec)\n  - Zerveas、George、Srideepika Jayaraman、Dhaval Patel、Anuradha Bhamidipaty 和 Carsten Eickhoff。*AAAI 2022*\n\n## 图\n - 深度图信息最大化\n   [[pdf]](https:\u002F\u002Fopenreview.net\u002Fforum?id=rklz9iAcKQ)\n   [[code]](https:\u002F\u002Fgithub.com\u002FPetarV-\u002FDGI)\n   - Petar Veličković, William Fedus, William L. Hamilton, Pietro Liò, Yoshua Bengio, R Devon Hjelm. *ICLR 2019*\n\n - 自监督学习何时有助于图卷积网络\n   [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.09136.pdf)\n   - Yuning You, Tianlong Chen, Zhangyang Wang, Yang Shen. *ICML 2020*\n\n - 针对标签稀少图的图卷积网络多阶段自监督学习\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1902.11038v2.pdf)\n   - Ke Sun, Zhouchen Lin, Zhanxing Zhu. *AAAI 2020*\n\n - 利用自监督边特征和图神经网络深入了解SARS-CoV-2感染及COVID-19严重程度\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.12971v1.pdf)\n   - Arijit Sehanobish, Neal G. Ravindra, David van Dijk. *ICML 2020研讨会*\n\n - 深度图对比表示学习\n    [[pdf]](http:\u002F\u002Farxiv.org\u002Fabs\u002F2006.04131)\n    [[code]](https:\u002F\u002Fgithub.com\u002FCRIPAC-DIG\u002FGRACE)\n   - Yanqiao Zhu, Yichen Xu, Feng Yu, Qiang Liu, Shu Wu, Liang Wang. *ICML 2020研讨会*\n\n - 图上的对比多视图表示学习\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.05582)\n   - Kaveh Hassani, Amir Hosein Khasahmadi. *ICML 2020*\n\n - GCC: 用于图神经网络预训练的图对比编码\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.09963.pdf)\n   - Jiezhong Qiu, Qibin Chen, Yuxiao Dong. *KDD 2020*\n\n - GPT-GNN: 图神经网络的生成式预训练\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.15437.pdf)\n    [[code]](https:\u002F\u002Fgithub.com\u002Facbull\u002FGPT-GNN)\n   - Ziniu Hu, Yuxiao Dong, Kuansan Wang, Kai-Wei Chang, Yizhou Sun. *KDD 2020*\n\n - 图上的自监督学习：深度见解与新方向\n    [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.10141.pdf)\n   - Wei Jin, Tyler Derr, Haochen Liu, Yiqi Wang, Suhang Wang, Zitao Liu, Jiliang Tang。\n\n- 异质网络中用于链接预测的上下文嵌入自监督学习\n  [[pdf]](https:\u002F\u002Fpeople.cs.vt.edu\u002F~reddy\u002Fpapers\u002FWWW21.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Fpnnl\u002FSLICE)\n  - Ping Wang, Khushbu Agarwal, Colby Ham, Sutanay Choudhury，以及 Chandan K. Reddy。*WWW 2021*\n\n- 基于知识图谱逻辑查询的双曲空间自监督表示学习\n  [[pdf]](https:\u002F\u002Fpeople.cs.vt.edu\u002F~reddy\u002Fpapers\u002FWWW21a.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002Famazon-research\u002Fhyperbolic-embeddings)\n  - Nurendra Choudhary, Nikhil Rao, Sumeet Katariya, Karthik Subbian，以及 Chandan K. Reddy。*WWW 2021*\n\n- GraphMAE：自监督掩码图自动编码器\n  [[pdf]](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2205.10803.pdf)\n  [[code]](https:\u002F\u002Fgithub.com\u002FTHUDM\u002FGraphMAE)\n  - Zhenyu Hou, Xiao Liu, Yukuo Ceng, Yuxiao Dong, Hongxia Yang, Chunjie Wang，以及 Jie Tang。*KDD 2022*\n\n## 讲座\n- 自学习系统的力量。Demis Hassabis（DeepMind）。\n  [[link]](https:\u002F\u002Fyoutu.be\u002Fwxis9FrCHbw)\n- 超大规模自监督学习：无需人类监督即可学习感知与行动。Abhinav Gupta（CMU）。\n  [[link]](https:\u002F\u002Fsimons.berkeley.edu\u002Ftalks\u002Fabhinav-gupta-2017-3-28)\n- 自监督、元监督、好奇心：让计算机更努力地学习。Alyosha Efros（UCB）\n  [[link]](https:\u002F\u002Fbusiness.facebook.com\u002Facademics\u002Fvideos\u002F1632981350086599)\n- 无监督视觉学习教程。*CVPR 2018*\n  [[第一部分]](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=gSqmUOAMwcc)\n  [[第二部分]](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=BijK_US6A0w)\n- 自监督学习。Andrew Zisserman（牛津大学 & Deepmind）。\n  [[pdf]](https:\u002F\u002Fproject.inria.fr\u002Fpaiss\u002Ffiles\u002F2018\u002F07\u002Fzisserman-self-supervised.pdf)\n- 图嵌入、内容理解与自监督学习。Yann LeCun。（NYU & FAIR）\n  [[pdf]](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F12pDCno02FJPDEBk4iGuuaj8b2rr48Hh0\u002Fview)\n  [[video]](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=UGPT64wo7lU)\n- 自监督学习：机器能否像人类一样学习？Yann LeCun @EPFL。\n  [[video]](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=7I0Qt7GALVk)\n- 第9周（b）：CS294-158深度无监督学习（2019年春季）。Alyosha Efros @UC Berkeley。\n  [[video]](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=PX11C5Vfo9U)\n\n## 学位论文\n- 用于视觉表征学习的超越手动标注的监督方式。Carl Doersch。[[pdf]](http:\u002F\u002Fwww.carldoersch.com\u002Fdocs\u002Fthesis.pdf)。\n- 用于自监督视觉表征学习的图像合成。Richard Zhang。[[pdf]](https:\u002F\u002Fwww2.eecs.berkeley.edu\u002FPubs\u002FTechRpts\u002F2018\u002FEECS-2018-36.pdf)。\n- 不受直接监督的视觉学习。Tinghui Zhou。[[pdf]](https:\u002F\u002Fwww2.eecs.berkeley.edu\u002FPubs\u002FTechRpts\u002F2018\u002FEECS-2018-128.pdf)。\n- 极少人类监督下的视觉学习。Ishan Misra。[[pdf]](https:\u002F\u002Fwww.ri.cmu.edu\u002Fpublications\u002Fvisual-learning-with-minimal-human-supervision\u002F)。\n\n## 博客\n- 自监督表示学习。Lilian Weng。[[link]](https:\u002F\u002Flilianweng.github.io\u002Flil-log\u002F2019\u002F11\u002F10\u002Fself-supervised-learning.html)。\n- 自监督表示学习在NLP中的应用。Amit Chaudhary。[[link]](https:\u002F\u002Famitness.com\u002F2020\u002F05\u002Fself-supervised-learning-nlp\u002F)。\n- 插图版[[自监督学习]](https:\u002F\u002Famitness.com\u002F2020\u002F02\u002Fillustrated-self-supervised-learning\u002F)、[[SimCLR]](https:\u002F\u002Famitness.com\u002F2020\u002F03\u002Fillustrated-simclr\u002F)、[[PIRL]](https:\u002F\u002Famitness.com\u002F2020\u002F03\u002Fillustrated-pirl\u002F)、[[自标记]](https:\u002F\u002Famitness.com\u002F2020\u002F04\u002Fillustrated-self-labelling\u002F)、[[FixMatch]](https:\u002F\u002Famitness.com\u002F2020\u002F03\u002Ffixmatch-semi-supervised\u002F)、[[DeepCluster]](https:\u002F\u002Famitness.com\u002F2020\u002F04\u002Fdeepcluster\u002F)。Amit Chaudhary。\n- 对比自监督学习。Ankesh Anand。[[link]](https:\u002F\u002Fankeshanand.com\u002Fblog\u002F2020\u002F01\u002F26\u002Fcontrative-self-supervised-learning.html)。\n\n## 许可\n在法律允许的最大范围内，[Zhongzheng Ren](https:\u002F\u002Fjason718.github.io\u002F)已放弃其对该作品的所有版权及相关或邻接权利。","# Awesome Self-Supervised Learning 快速上手指南\n\n`awesome-self-supervised-learning` 并非一个可直接安装的单一软件包或库，而是一个**精选资源列表**（Curated List），汇集了自监督学习领域的论文、代码库、综述和教程。本指南将指导你如何利用该列表找到适合的工具并运行相关代码。\n\n## 环境准备\n\n由于列表中包含不同年份和框架（PyTorch, TensorFlow, Caffe 等）的项目，建议根据你具体选择的论文\u002F项目进行环境配置。以下是通用的推荐环境：\n\n*   **操作系统**: Linux (Ubuntu 18.04+\u002F20.04+) 或 macOS\n*   **Python**: 3.7 - 3.10 (具体版本视目标项目而定)\n*   **核心依赖**:\n    *   PyTorch 或 TensorFlow (大多数现代项目基于 PyTorch)\n    *   CUDA & cuDNN (如需 GPU 加速)\n    *   Git (用于克隆代码库)\n*   **推荐工具**:\n    *   `conda` 或 `venv` (用于隔离虚拟环境)\n    *   `pip` (包管理)\n\n> **国内加速建议**:\n> *   **PyTorch 安装**: 推荐使用清华源或中科大源。\n>     ```bash\n>     pip install torch torchvision torchaudio --index-url https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n>     ```\n> *   **Git 克隆**: 若 GitHub 访问缓慢，可使用镜像站（如 `https:\u002F\u002Fgithub.com.cnpmjs.org`）替换原域名，或使用代理。\n\n## 安装步骤\n\n由于这是一个资源索引，没有统一的安装命令。请按照以下步骤获取具体项目的代码：\n\n1.  **浏览列表**:\n    访问项目主页或在本地查看 README，根据任务类型（如图像表示学习、NLP、理论分析等）找到感兴趣的论文。\n\n2.  **定位代码仓库**:\n    在列表中找到对应条目，点击 `[[code]]` 链接跳转到 GitHub 仓库。\n    *   示例条目格式：\n        ```markdown\n        - Unsupervised Visual Representation Learning by Context Prediction.\n          [[pdf]](link) \n          [[code]](http:\u002F\u002Fgraphics.cs.cmu.edu\u002Fprojects\u002FdeepContext\u002F)\n        ```\n\n3.  **克隆项目**:\n    使用 Git 克隆选中的仓库到本地。\n    ```bash\n    git clone \u003C目标仓库的 URL>\n    cd \u003C目标仓库目录>\n    ```\n\n4.  **安装项目依赖**:\n    进入项目目录后，通常通过 `requirements.txt` 安装依赖。\n    ```bash\n    # 通用安装命令\n    pip install -r requirements.txt\n    \n    # 若使用国内源加速\n    pip install -r requirements.txt -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n    ```\n    *注意：部分老旧项目可能需要特定的框架版本（如 TensorFlow 1.x），请仔细阅读该项目自带的 `README.md`。*\n\n## 基本使用\n\n每个项目的具体用法不同，但通常遵循“数据准备 -> 预训练 -> 评估”的流程。以下以列表中经典的 **Context Encoders** (CVPR 2016) 或类似的现代对比学习项目为例，展示通用操作模式：\n\n### 1. 准备数据集\n大多数自监督学习项目需要大型数据集（如 ImageNet, CIFAR-10）。你需要下载数据并放置在项目指定的目录下。\n```bash\n# 示例：创建数据目录\nmkdir -p data\u002Fcifar10\n# (此处需手动下载数据集或使用项目提供的下载脚本)\n```\n\n### 2. 运行预训练 (Pre-training)\n执行自监督学习任务（无标签训练）。\n```bash\n# 示例命令（具体参数请参考各项目的 README）\npython train.py --dataset cifar10 --method context_encoder --epochs 200\n```\n\n### 3. 线性评估 (Linear Evaluation)\n验证学到的特征表示质量。通常在冻结骨干网络的情况下，训练一个简单的线性分类器。\n```bash\n# 示例命令\npython eval_linear.py --checkpoint .\u002Fcheckpoints\u002Fbest_model.pth --dataset cifar10\n```\n\n### 4. 查看理论资源\n如果你关注理论基础而非代码实现，直接点击列表中的 `[[pdf]]` 链接阅读论文即可。例如阅读 2024 年的最新理论分析：\n*   *Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning*\n*   *Matrix Information Theory for Self-Supervised Learning*\n\n---\n**提示**: 该列表更新频繁，涵盖从 2015 年至今的前沿工作。对于初学者，建议从 **\"Computer Vision -> Survey\"** 章节中的综述论文入手，建立整体认知后再选择具体的代码项目进行复现。","某医疗影像初创公司的算法团队正试图开发一个肺炎检测模型，但面临海量未标注的胸部 X 光片和极少量确诊病例数据的困境。\n\n### 没有 awesome-self-supervised-learning 时\n- **资源搜集低效**：团队成员需花费数周在 arXiv 和 GitHub 上盲目搜索，难以区分哪些自监督学习（SSL）论文真正适用于医学图像，极易遗漏关键前沿成果。\n- **理论理解门槛高**：面对对比学习等复杂概念，缺乏系统性的理论综述指引，导致团队在“对齐性”与“均匀性”等核心机制上反复试错，浪费大量算力。\n- **代码复现困难**：找到的论文往往缺少官方代码链接或实现细节模糊，工程师不得不从零重写算法，严重拖慢了从预训练到微调的开发周期。\n- **领域适配迷茫**：不清楚如何将通用的 SSL 方法迁移到特殊的 3D CT 扫描或时间序列生命体征数据上，缺乏跨领域的成功案例参考。\n\n### 使用 awesome-self-supervised-learning 后\n- **一站式资源获取**：团队直接利用其分类清晰的目录，快速锁定了针对图像表示学习的最新 SOTA 方法（如 SimCLR、MoCo 的变体），将调研时间从数周缩短至两天。\n- **理论路径清晰**：通过\"Theory\"板块中精选的 ICML、CVPR 理论分析论文，团队迅速理解了损失函数的数学本质，从而能更精准地调整超参数。\n- **开箱即用体验**：列表中每个项目都附带经过验证的代码仓库链接，工程师直接复用成熟框架进行无标签数据的预训练，大幅降低了工程落地难度。\n- **跨模态灵感激发**：参考列表中关于 3D 特征学习和时间序列的章节，团队成功将视频表示学习的技术迁移应用到动态超声影像分析中，提升了模型泛化能力。\n\nawesome-self-supervised-learning 通过构建结构化的知识图谱，将分散的前沿研究转化为可执行的工程资产，让团队在数据稀缺场景下也能高效构建高性能 AI 模型。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjason718_awesome-self-supervised-learning_d44db243.png","jason718","Jason Ren","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fjason718_9033c5af.jpg",null,"Ai2\u002FUW","Seattle","https:\u002F\u002Fgithub.com\u002Fjason718",6378,838,"2026-04-02T08:36:45",1,"","未说明",{"notes":89,"python":87,"dependencies":90},"该仓库是一个自监督学习（Self-Supervised Learning）资源的精选列表（Awesome List），主要包含论文、综述、代码库链接和演讲资源，本身不是一个可直接运行的单一软件工具。因此，README 中未提供具体的操作系统、GPU、内存、Python 版本或依赖库的安装需求。具体的运行环境需参考列表中各个独立项目（如 FAIR Benchmark, JULE, BigAN 等）的各自文档。",[],[13,14,26,54],[93,94,95,96,97,98,99],"machine-learning","computer-vision","self-supervised","reinforcement-learning","robotics","natural-language-processing","deep-learning","2026-03-27T02:49:30.150509","2026-04-06T06:53:23.182150",[],[]]