{"id":16720697,"url":"https://github.com/zhmiao/opencompounddomainadaptation-ocda","last_synced_at":"2025-07-23T05:35:14.982Z","repository":{"id":69140760,"uuid":"250958880","full_name":"zhmiao/OpenCompoundDomainAdaptation-OCDA","owner":"zhmiao","description":"Pytorch implementation for \"Open Compound Domain Adaptation\" (CVPR 2020 ORAL)","archived":false,"fork":false,"pushed_at":"2021-09-19T07:16:36.000Z","size":1605,"stargazers_count":139,"open_issues_count":8,"forks_count":15,"subscribers_count":7,"default_branch":"master","last_synced_at":"2025-04-02T02:13:07.076Z","etag":null,"topics":["computer-vision","cvpr2020","deep-learning","domain-adaptation","ocda","open-compound-domain-adaptation","pytorch-implementation"],"latest_commit_sha":null,"homepage":"https://liuziwei7.github.io/projects/CompoundDomain.html","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/zhmiao.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-03-29T05:13:35.000Z","updated_at":"2024-01-04T16:44:01.000Z","dependencies_parsed_at":null,"dependency_job_id":"2d7ecb58-f4e4-440f-a483-a7008b429ec1","html_url":"https://github.com/zhmiao/OpenCompoundDomainAdaptation-OCDA","commit_stats":{"total_commits":23,"total_committers":3,"mean_commits":7.666666666666667,"dds":0.4782608695652174,"last_synced_commit":"eb115b608d70d3a36eac4bc12dd0098ecb804175"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/zhmiao/OpenCompoundDomainAdaptation-OCDA","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhmiao%2FOpenCompoundDomainAdaptation-OCDA","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhmiao%2FOpenCompoundDomainAdaptation-OCDA/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhmiao%2FOpenCompoundDomainAdaptation-OCDA/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhmiao%2FOpenCompoundDomainAdaptation-OCDA/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zhmiao","download_url":"https://codeload.github.com/zhmiao/OpenCompoundDomainAdaptation-OCDA/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zhmiao%2FOpenCompoundDomainAdaptation-OCDA/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266624869,"owners_count":23958303,"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","status":"online","status_checked_at":"2025-07-23T02:00:09.312Z","response_time":66,"last_error":null,"robots_txt_status":null,"robots_txt_updated_at":null,"robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["computer-vision","cvpr2020","deep-learning","domain-adaptation","ocda","open-compound-domain-adaptation","pytorch-implementation"],"created_at":"2024-10-12T22:08:13.185Z","updated_at":"2025-07-23T05:35:14.956Z","avatar_url":"https://github.com/zhmiao.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Open Compound Domain Adaptation\n\n[[Project]](https://liuziwei7.github.io/projects/CompoundDomain.html) [[Paper]](https://arxiv.org/abs/1909.03403) [[Demo]](https://www.youtube.com/watch?v=YcmgCCRA1qc) [[Blog]](https://bair.berkeley.edu/blog/2020/06/14/ocda/)\n\n## Overview\n`Open Compound Domain Adaptation (OCDA)` is the author's re-implementation of the compound domain adaptator described in:  \n\"[Open Compound Domain Adaptation](https://arxiv.org/abs/1909.03403)\"   \n[Ziwei Liu](https://liuziwei7.github.io/)\u003csup\u003e\\*\u003c/sup\u003e,\u0026nbsp; [Zhongqi Miao](https://github.com/zhmiao)\u003csup\u003e\\*\u003c/sup\u003e,\u0026nbsp; [Xingang Pan](https://xingangpan.github.io/),\u0026nbsp; [Xiaohang Zhan](https://xiaohangzhan.github.io/),\u0026nbsp; [Dahua Lin](http://dahua.me/),\u0026nbsp; [Stella X. Yu](https://www1.icsi.berkeley.edu/~stellayu/),\u0026nbsp; [Boqing Gong](http://boqinggong.info/)\u0026nbsp; (CUHK \u0026 Berkeley \u0026 Google)\u0026nbsp; \nin IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020, **Oral Presentation**\n\n\u003cimg src='./assets/intro.png' width=900\u003e\n\nFurther information please contact [Zhongqi Miao](mailto:zhongqi.miao@berkeley.edu) and [Ziwei Liu](https://liuziwei7.github.io/).\n\n## Requirements\n* [PyTorch](https://pytorch.org/) (version \u003e= 0.4.1)\n* [scikit-learn](https://scikit-learn.org/stable/)\n\n## Updates:\n* 11/09/2020: We have uploaded C-Faces dataset. Corresponding codes will be updated shortly. Please be patient. Thank you very much!\n* 06/16/2020: We have released C-Digits dataset and corresponding weights. \n\n## Data Preparation\n\n\u003cimg src='./assets/dataset.png' width=500\u003e\n\n[[OCDA Datasets]](https://drive.google.com/drive/folders/1_uNTF8RdvhS_sqVTnYx17hEOQpefmE2r?usp=sharing)\n\nFirst, please download [C-Digits](https://drive.google.com/file/d/1ro-up5YDq1Cm9n_JaOG9pRbfPYVxcV8P/view?usp=sharing), save it to a directory, and change the dataset root in the config file accordingly.\nThe file contains MNIST, MNIST-M, SVHN, SVHN-bal, and SynNum. \n\nFor C-Faces, please download [Multi-PIE](http://www.cs.cmu.edu/afs/cs/project/PIE/MultiPie/Multi-Pie/Home.html) first. Since it is a proprietary dataset, we can only privide the data list we used during training [here](https://drive.google.com/file/d/1OGPAJz5OXelzRE0kEhyU8h4cqgbewj_r/view?usp=sharing). We will update the dataset function accordingly. \n\n\n## Getting Started (Training \u0026 Testing)\n\n\u003cimg src='./assets/pipeline.png' width=900\u003e\n\n### C-Digits\n\nTo run experiments for both training and evaluation on the C-Digits datasets (SVHN -\u003e Multi):\n```bash\npython main.py --config ./config svhn_bal_to_multi.yaml\n```\nAfter training is completed, the same command will automatically evaluate the trained models.\n\n### C-Faces\n\n* We will be releasing code for C-Faces experiements very soon.\n\n### C-Driving\n\n* Please refer to: https://github.com/XingangPan/OCDA-Driving-Example .\n\n## Reproduced Benchmarks and Model Zoo \n\nNOTE: All reproduced weights need to be decompressed into results directory:\n```\nOpenCompoundedDomainAdaptation-OCDA\n    |--results\n```\n\n### C-Digits (Results may currently have variations.)\n\n|  Source  |    MNIST (C)   |  MNIST-M (C)  |   USPS (C)  |  SymNum (O)  |   Avg. Acc   |      Download      |\n| :------: | :------------: | :-----------: | :---------: | :----------: | :----------: | :----------------: |\n|   SVHN   |      89.62     |     64.53     |    81.17    |    87.86     |    80.80     |      [model](https://drive.google.com/file/d/1RCMYC-NBwZQnPcDXIEIqn_z8EsDqv1a2/view?usp=sharing)     |\n\n## License and Citation\nThe use of this software is released under [BSD-3](https://github.com/zhmiao/OpenCompoundDomainAdaptation-OCDA/blob/master/LICENSE).\n```\n@inproceedings{compounddomainadaptation,\n  title={Open Compound Domain Adaptation},\n  author={Liu, Ziwei and Miao, Zhongqi and Pan, Xingang and Zhan, Xiaohang and Lin, Dahua and Yu, Stella X. and Gong, Boqing},\n  booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},\n  year={2020}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzhmiao%2Fopencompounddomainadaptation-ocda","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzhmiao%2Fopencompounddomainadaptation-ocda","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzhmiao%2Fopencompounddomainadaptation-ocda/lists"}