{"id":19666713,"url":"https://github.com/open-mmlab/openunreid","last_synced_at":"2025-08-17T18:40:22.562Z","repository":{"id":43910121,"uuid":"266675271","full_name":"open-mmlab/OpenUnReID","owner":"open-mmlab","description":"PyTorch open-source toolbox for unsupervised or domain adaptive object re-ID.","archived":false,"fork":false,"pushed_at":"2021-06-14T08:43:21.000Z","size":651,"stargazers_count":402,"open_issues_count":23,"forks_count":68,"subscribers_count":12,"default_branch":"master","last_synced_at":"2025-03-30T05:09:40.069Z","etag":null,"topics":["domain-translation","image-retrieval","open-set-domain-adaptation","pseudo-labeling","re-identification","unsupervised-domain-adaptation","unsupervised-learning"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/open-mmlab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-05-25T03:33:45.000Z","updated_at":"2025-03-19T02:35:38.000Z","dependencies_parsed_at":"2022-07-26T15:45:11.890Z","dependency_job_id":null,"html_url":"https://github.com/open-mmlab/OpenUnReID","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/open-mmlab%2FOpenUnReID","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/open-mmlab%2FOpenUnReID/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/open-mmlab%2FOpenUnReID/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/open-mmlab%2FOpenUnReID/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/open-mmlab","download_url":"https://codeload.github.com/open-mmlab/OpenUnReID/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247445670,"owners_count":20939958,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["domain-translation","image-retrieval","open-set-domain-adaptation","pseudo-labeling","re-identification","unsupervised-domain-adaptation","unsupervised-learning"],"created_at":"2024-11-11T16:28:41.609Z","updated_at":"2025-04-06T07:11:54.162Z","avatar_url":"https://github.com/open-mmlab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cimg src=\"docs/open_mmlab.png\" align=\"right\" width=\"30%\"\u003e\n\n# OpenUnReID\n\n## Introduction\n`OpenUnReID` is an open-source PyTorch-based codebase for both unsupervised learning (**USL**) and unsupervised domain adaptation (**UDA**) in the context of object re-ID tasks. It provides strong baselines and multiple state-of-the-art methods with highly refactored codes for both *pseudo-label-based* and *domain-translation-based* frameworks. It works with **Python \u003e=3.5** and **PyTorch \u003e=1.1**.\n\nWe are actively updating this repo, and more methods will be supported soon. Contributions are welcome.\n\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"docs/openunreid.png\" width=\"60%\"\u003e\n\u003c/p\u003e\n\n### Major features\n- [x] Distributed training \u0026 testing with multiple GPUs and multiple machines.\n- [x] High flexibility on various combinations of datasets, backbones, losses, etc.\n- [x] GPU-based pseudo-label generation and k-reciprocal re-ranking with quite high speed.\n- [x] Plug-and-play domain-specific BatchNorms for any backbones, sync BN is also supported.\n- [x] Mixed precision training is supported, achieving higher efficiency.\n- [x] A strong cluster baseline, providing high extensibility on designing new methods.\n- [x] State-of-the-art methods and performances for both USL and UDA problems on object re-ID.\n\n### Supported methods\n\nPlease refer to [MODEL_ZOO.md](docs/MODEL_ZOO.md) for trained models and download links, and please refer to [LEADERBOARD.md](docs/LEADERBOARD.md) for the leaderboard on public benchmarks.\n\n| Method | Reference | USL | UDA |\n| ------ | :---: | :-----: | :-----: |\n| [UDA_TP](tools/UDA_TP) | [PR'20 (arXiv'18)](https://arxiv.org/abs/1807.11334) | ✓ | ✓ |\n| [SPGAN](tools/SPGAN)  | [CVPR'18](https://arxiv.org/abs/1711.07027) | n/a  |  ✓ |  \n| SSG | [ICCV'19](https://arxiv.org/abs/1811.10144) | ongoing  | ongoing  |  \n| [strong_baseline](tools/strong_baseline) | Sec. 3.1 in [ICLR'20](https://openreview.net/pdf?id=rJlnOhVYPS) | ✓ | ✓ |\n| [MMT](tools/MMT/) | [ICLR'20](https://openreview.net/pdf?id=rJlnOhVYPS) | ✓  | ✓  |  \n| [SpCL](tools/SpCL/) | [NeurIPS'20](https://arxiv.org/abs/2006.02713) | ✓ |  ✓  |  \n| SDA  | [arXiv'20](https://arxiv.org/abs/2003.06650) | n/a  |  ongoing |  \n\n\n## Updates\n\n[2020-08-02] Add the leaderboard on public benchmarks: [LEADERBOARD.md](docs/LEADERBOARD.md)\n\n[2020-07-30] `OpenUnReID` v0.1.1 is released:\n+ Support domain-translation-based frameworks, [CycleGAN](tools/CycleGAN) and [SPGAN](tools/SPGAN).\n+ Support mixed precision training (`torch.cuda.amp` in PyTorch\u003e=1.6), use it by adding `TRAIN.amp True` at the end of training commands.\n\n[2020-07-01] `OpenUnReID` v0.1.0 is released.\n\n## Installation\n\nPlease refer to [INSTALL.md](docs/INSTALL.md) for installation and dataset preparation.\n\n## Get Started\n\nPlease refer to [GETTING_STARTED.md](docs/GETTING_STARTED.md) for the basic usage of `OpenUnReID`.\n\n## License\n\n`OpenUnReID` is released under the [Apache 2.0 license](LICENSE).\n\n## Citation\n\nIf you use this toolbox or models in your research, please consider cite:\n```\n@inproceedings{ge2020mutual,\n  title={Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification},\n  author={Yixiao Ge and Dapeng Chen and Hongsheng Li},\n  booktitle={International Conference on Learning Representations},\n  year={2020},\n  url={https://openreview.net/forum?id=rJlnOhVYPS}\n}\n\n@inproceedings{ge2020selfpaced,\n    title={Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID},\n    author={Yixiao Ge and Feng Zhu and Dapeng Chen and Rui Zhao and Hongsheng Li},\n    booktitle={Advances in Neural Information Processing Systems},\n    year={2020}\n}\n```\n\u003c!-- @misc{ge2020structured,\n    title={Structured Domain Adaptation with Online Relation Regularization for Unsupervised Person Re-ID},\n    author={Yixiao Ge and Feng Zhu and Rui Zhao and Hongsheng Li},\n    year={2020},\n    eprint={2003.06650},\n    archivePrefix={arXiv},\n    primaryClass={cs.CV}\n} --\u003e\n\n\n## Acknowledgement\n\nSome parts of `openunreid` are learned from [torchreid](https://github.com/KaiyangZhou/deep-person-reid) and [fastreid](https://github.com/JDAI-CV/fast-reid). We would like to thank for their projects, which have boosted the research of supervised re-ID a lot. We hope that `OpenUnReID` could well benefit the research community of unsupervised re-ID by providing strong baselines and state-of-the-art methods.\n\n## Contact\n\nThis project is developed by Yixiao Ge ([@yxgeee](https://github.com/yxgeee)), Tong Xiao ([@Cysu](https://github.com/Cysu)), Zhiwei Zhang ([@zwzhang121](https://github.com/zwzhang121)).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopen-mmlab%2Fopenunreid","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fopen-mmlab%2Fopenunreid","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopen-mmlab%2Fopenunreid/lists"}