{"id":13737581,"url":"https://github.com/tim-learn/ATDOC","last_synced_at":"2025-05-08T14:33:04.954Z","repository":{"id":113171607,"uuid":"321011270","full_name":"tim-learn/ATDOC","owner":"tim-learn","description":"code released for our CVPR 2021 paper \"Domain Adaptation with Auxiliary Target Domain-Oriented Classifier\"","archived":false,"fork":false,"pushed_at":"2023-05-23T12:13:23.000Z","size":68,"stargazers_count":55,"open_issues_count":1,"forks_count":9,"subscribers_count":5,"default_branch":"main","last_synced_at":"2024-11-15T06:32:05.774Z","etag":null,"topics":["cvpr2021","domain-adaptation","semi-supervised","transfer-learning"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tim-learn.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}},"created_at":"2020-12-13T07:44:59.000Z","updated_at":"2024-07-23T08:41:33.000Z","dependencies_parsed_at":null,"dependency_job_id":"65c88001-6a50-4742-a89c-b4041ae31206","html_url":"https://github.com/tim-learn/ATDOC","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/tim-learn%2FATDOC","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tim-learn%2FATDOC/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tim-learn%2FATDOC/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tim-learn%2FATDOC/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tim-learn","download_url":"https://codeload.github.com/tim-learn/ATDOC/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253085771,"owners_count":21851697,"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":["cvpr2021","domain-adaptation","semi-supervised","transfer-learning"],"created_at":"2024-08-03T03:01:54.004Z","updated_at":"2025-05-08T14:33:04.499Z","avatar_url":"https://github.com/tim-learn.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# Official implementation for **ATDOC**\n\n[**[CVPR-2021] Domain Adaptation with Auxiliary Target Domain-Oriented Classifier**](https://arxiv.org/pdf/2007.04171.pdf)\n\n[Update @ Nov 23 2021] \n\n1. **[For Office, please change the *max-epoch* to 100; for VISDA-C, change the *max-epoch* to 1 and change the *net* to resnet101]**\n2. **Add the code associated with SSDA, change the *max-epoch* to 20 for DomainNet-126**\n3. **Thank @lyxok1 for pointing out the typo in Eq.(6), we have corrected it in the new verison of this paper.**\n\n\n\nBelow is the demo for **ATDOC** on a UDA task of Office-Home [*max_epoch* to 50]:\n\n\n1. installing packages\n\n   `python == 3.6.8`\n   `pytorch ==1.1.0`\n   `torchvision == 0.3.0`\n   `numpy, scipy, sklearn, PIL, argparse, tqdm`\n   \n2. download the Office-Home dataset\n\n   `mkdir dataset`\n\n   `cd dataset`\n\n   `pip install gdown`\n\n   `gdown https://drive.google.com/u/0/uc?id=0B81rNlvomiwed0V1YUxQdC1uOTg\u0026export=download`\n\n   `unzip OfficeHomeDataset_10072016.zip`\n\n   `mv ./OfficeHomeDataset_10072016/Real\\ World ./OfficeHomeDataset_10072016/RealWorld`\n\n   `cd ../`\n\n3. run the main file with '**Source-model-only**'\n\n   `python demo_uda.py --pl none --dset office-home --max_epoch 50 --s 0 --t 1 --gpu_id 0 --method srconly --output logs/uda/run1/`\n\n4. run the main file with '**ATDOC-NC**'\n\n   `python demo_uda.py --pl atdoc_nc --tar_par 0.1 --dset office-home --max_epoch 50 --s 0 --t 1 --gpu_id 0 --method srconly --output logs/uda/run1/`\n\n5. run the main file with '**ATDOC-NA**'\n\n   `python demo_uda.py --pl atdoc_na --tar_par 0.2 --dset office-home --max_epoch 50 --s 0 --t 1 --gpu_id 0 --method srconly --output logs/uda/run1/`\n\n6. run the main file with '**ATDOC-NA**' combined with '**CDAN+E**'\n\n   `python demo_uda.py --pl atdoc_na --tar_par 0.2 --dset office-home --max_epoch 50 --s 0 --t 1 --gpu_id 0 --method CDANE --output logs/uda/run1/`\n\n7. run the main file with '**ATDOC-NA**' combined with '**MixMatch**'\n\n   `python demo_mixmatch.py --pl none --dset office-home  --max_epoch 50 --s 0 --t 1 --gpu_id 0 --output logs/uda/run1/`\n\n8. run the main file with '**ATDOC-NA**' combined with '**MixMatch**'\n\n   `python demo_mixmatch.py --pl atdoc_na --dset office-home  --max_epoch 50 --s 0 --t 1 --gpu_id 0 --output logs/uda/run1/`\n\n\n\n\n### Citation\n\nIf you find this code useful for your research, please cite our paper\n\n\u003e @inproceedings{liang2021domain,  \n\u003e  \u0026nbsp; \u0026nbsp;  title={Domain Adaptation with Auxiliary Target Domain-Oriented Classifier},  \n\u003e  \u0026nbsp; \u0026nbsp;  author={Liang, Jian and Hu, Dapeng and Feng, Jiashi},  \n\u003e  \u0026nbsp; \u0026nbsp;  booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},  \n\u003e  \u0026nbsp; \u0026nbsp;  year={2021}  \n\u003e }\n\u003e \n### Contact\n\n- [liangjian92@gmail.com](mailto:liangjian92@gmail.com)\n- [dapeng.hu@u.nus.edu](mailto:dapeng.hu@u.nus.edu)\n- [elefjia@nus.edu.sg](mailto:elefjia@nus.edu.sg)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftim-learn%2FATDOC","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftim-learn%2FATDOC","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftim-learn%2FATDOC/lists"}