🔥🔥 SARDet-100K 已被 NeurIPS 2024 接收为 spotlight 论文！！

🔥🔥 我们的新工作 RSAR 被 CVPR 2025 接收！！！

"RSAR: Restricted State Angle Resolver and Rotated SAR Benchmark"

该工作包含一个大规模多类别旋转 SAR（合成孔径雷达）目标检测数据集，是 SARDet-100K 的近似旋转标注版本。

本仓库现已支持 DenoDet！！

"DenoDet: Attention as Deformable Multi-Subspace Feature Denoising for Target Detection in SAR Images" 见：https://arxiv.org/pdf/2406.02833

Jittor 版本实现在 NK-JittorCV/nk-det

"SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection" 见：https://arxiv.org/pdf/2403.06534.pdf

李宇轩，李翔*，李玮杰，侯淇彬，刘丽，程明明，杨健*

走过路过不要错过！！

面对2024年的科研战场，你是否感到了前所未有的科研压力？计算机视觉的各大任务仿佛已经达到了饱和点，榜单一次又一次被那些拥有海量数据和计算资源的大模型所主宰。对于我们这些还在校园里奋斗的学生来说，手头的资源始终显得那么微不足道，似乎永远也竞争不过那些垄断科研的巨头。每一个方向似乎都被人挖得满满的，想发表一篇paper变得越来越难，快毕业的你是否也在焦虑地寻找一个真正属于自己的研究方向？多少次，我们都幻想能回到15年前ImageNet发布的那个夜晚，那时候没有群魔乱舞的注意力机制，也没有数以Billion计参数的大模型，每一个任务都是一片待开垦的蓝海……

但是今天，告诉你，有这么一个方向，曾一度因为缺乏大规模数据集和寥寥无几的开源代码而默默无闻，它的发展似乎一直滞后。但随着开源大规模数据集的诞生和完善的代码库的出现，之前的难题统统烟消云散。现在，就如同被一道闪电击中，穿越回了数年前，还有一片未被充分开发的蓝海正展现在你的眼前，等待你去探索、去征服。

所以，你想知道我说的是什么领域吗？今天，你不需要支付998，也不需要98，只需在 GitHub 上给我们一个Star，SAR目标检测的大礼包就能免费带回家！这里有你需要的一切：从大规模数据集到详尽的实现代码，我们都为你准备好了。是的，我在说的就是遥感目标检测的掌上明珠：SAR（合成孔径雷达）目标检测！可能听起来有些神秘，但这个领域的潜力和含金量，真正懂的人都心照不宣，DDDD，YYDS！它不仅完美契合当前的国家战略需求，而且无论是在科研界还是工业界，都有着广阔的应用前景和无限的可能性。近年来，在SAR检测领域发表文章变得更加容易，这预示着这一领域的迅速发展和对新思想、新技术的渴求。现在就加入SAR目标检测的行列吧！它就像15年前的比特币，20年前的房地产，现在入局不后悔！让我们一起驰骋在这片广袤的蓝海之中，探索它的未知之处，共同开拓它的无限可能！

Don't miss out as you pass by!

Facing the scientific research battlefield of 2024, do you feel unprecedented pressure in research? The major tasks in Computer Vision seem to have reached a saturation point, with the charts being dominated time and again by large models that have access to massive data and computational resources. For those of us still striving in academia, our resources always seem so insignificant, as if we could never compete with those giants monopolizing research. Every direction seems to be thoroughly explored, making it increasingly difficult to publish a paper. Are you, about to graduate, also anxiously looking for a research direction that truly belongs to you? How many times have we fantasized about going back to the night when ImageNet was released 15 years ago, when there was no chaotic dance of attention mechanisms, no models with billions of parameters, and every task was an uncharted blue ocean...

But today, let me tell you my friend, about a direction that once lingered in obscurity due to the lack of large-scale datasets and scarce open-source codes, its development seemed to be always lagging. But with the emergence of open-source large-scale datasets and comprehensive code libraries, all previous problems have vanished like smoke. Now, as if struck by lightning and transported back several years, there is an undeveloped blue ocean in front of you, waiting for you to explore and conquer.

So, do you want to know what field I am talking about? Today, you don't need to pay 998, not even 98, just give us a Star on GitHub, and the SAR object detection big gift pack can be taken home for free! Here you have everything you need: from large-scale datasets to detailed implementation codes, we have prepared everything for you. Yes, I am talking about the jewel in the crown of remote sensing target detection: SAR (Synthetic Aperture Radar) object detection! It might sound mysterious, but the potential and value of this field are well understood by those in the know. It not only perfectly matches the current national strategic needs but also has a wide range of applications and limitless possibilities in both the scientific and industrial communities. In recent years, publishing articles in the SAR detection field has become easier, indicating the rapid development of this field and its thirst for new ideas and technologies. Join the ranks of SAR object detection now! It's like Bitcoin 15 years ago, real estate 20 years ago, getting involved now is something you won't regret! Let's gallop together in this vast blue ocean, explore its unknowns, and jointly tap into its limitless possibilities!

摘要

合成孔径雷达（Synthetic Aperture Radar, SAR）目标检测因其不可替代的全天候成像能力而受到广泛关注。然而，该研究领域长期受限于公开数据集规模有限（大多包含少于2K张图像，且仅含单一类别目标）以及源代码难以获取。为应对这些挑战，我们构建了一个面向大规模 SAR 目标检测的新基准数据集及开源方法。我们的数据集 SARDet-100K 是通过对10个现有 SAR 检测数据集进行深入调研、收集与标准化整合而成，为研究提供了大规模且多样化的数据资源。据我们所知，SARDet-100K 是首个达到 COCO 级别的大规模多类别 SAR 目标检测数据集。基于这一高质量数据集，我们开展了全面实验，并揭示了 SAR 目标检测中的一个关键挑战：在 RGB 数据集上的预训练与在 SAR 数据集上的微调之间，在数据域和模型结构方面存在显著差异。为弥合这些差距，我们提出了一种新颖的多阶段滤波增强（Multi-Stage with Filter Augmentation, MSFA）预训练框架，从数据输入、域迁移和模型迁移三个角度系统性地解决上述问题。所提出的 MSFA 方法显著提升了 SAR 目标检测模型的性能，并在多种模型上展现出卓越的泛化能力与灵活性。本工作旨在为 SAR 目标检测领域的进一步发展铺平道路。

引言

本仓库是论文 "SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection" 的官方代码库，论文地址：https://arxiv.org/pdf/2403.06534.pdf

数据集下载地址：

（训练集、验证集、测试集）

• 百度网盘：数据集
• OneDrive：数据集

模型权重下载地址：

• 百度网盘：模型
• OneDrive：模型

（目前仅发布了训练集和验证集。）

MSFA：多阶段滤波增强（Multi-Stage with Filter Augmentation）预训练框架

简介

本仓库是论文《SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection》中提出的多阶段滤波增强（MSFA）预训练框架的官方实现。

滤波增强（Filter Augmentation）代码位于 MSFA/msfa/models/backbones/MSFA.py。
SARDet-100K 数据集相关代码位于 MSFA/msfa/datasets/SAR_Det.py。
论文中使用的训练/测试配置文件位于 local_configs 目录下。

结果与模型

AI 工具分析助手

你是一个专业的 AI 工具分析助手，擅长将英文技术内容翻译和整理为中文。

# 进入项目主代码目录
cd MSFA

# 创建环境
conda create -y -n MSFA python=3.8
conda activate MSFA

# 安装 PyTorch
conda install pytorch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 pytorch-cuda=11.8 -c pytorch -c nvidia
# 或者
pip install torch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 --index-url https://download.pytorch.org/whl/cu118

# 安装 OpenMMLab 相关依赖
pip install -U openmim
mim install "mmengine==0.8.4"
mim install "mmcv==2.0.1"
mim install "mmdet==3.1.0"

# 安装其他依赖
pip install -r requirements.txt

# 安装 MSFA
pip install -v -e .

@inproceedings{li2024sardet100k,
	title={SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection}, 
	author={Yuxuan Li and Xiang Li and Weijie Li and Qibin Hou and Li Liu and Ming-Ming Cheng and Jian Yang},
	year={2024},
	booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS)},
}

@article{zhang2025rsar,
  title={RSAR: Restricted State Angle Resolver and Rotated SAR Benchmark},
  author={Zhang, Xin and Yang, Xue and Li, Yuxuan and Yang, Jian and Cheng, Ming-Ming and Li, Xiang},
  journal={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
  year={2025}
}

@article{dai2024denodet,
	title={DenoDet: Attention as Deformable Multi-Subspace Feature Denoising for Target Detection in SAR Images},
	author={Dai, Yimian and Zou, Minrui and Li, Yuxuan and Li, Xiang and Ni, Kang and Yang, Jian},
	journal={arXiv preprint arXiv:2406.02833},
	year={2024}
}

# 克隆仓库
git clone https://github.com/zhasion/SARDet_100K.git
cd SARDet_100K

# 创建并激活虚拟环境（可选但推荐）
python -m venv sardet_env
source sardet_env/bin/activate  # Linux/macOS
# 或 sardet_env\Scripts\activate  # Windows

# 安装依赖（使用国内镜像加速）
pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple

# 安装 COCO API（如需评估）
pip install pycocotools -i https://pypi.tuna.tsinghua.edu.cn/simple

data/
├── train/
├── val/
└── annotations/
    ├── instances_train.json
    └── instances_val.json

cd MSFA
python train.py \
  --dataset sardet100k \
  --data-path ../data \
  --model msfa_resnet50 \
  --batch-size 8 \
  --epochs 12 \
  --lr 0.01

python inference.py \
  --model msfa_resnet50 \
  --weights ../checkpoints/msfa_resnet50.pth \
  --input ../data/val/your_image.png \
  --output result.jpg