{"id":13737579,"url":"https://github.com/tim-learn/BA3US","last_synced_at":"2025-05-08T14:33:10.895Z","repository":{"id":46656720,"uuid":"283491951","full_name":"tim-learn/BA3US","owner":"tim-learn","description":"code for our ECCV 2020 paper \"A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation\"","archived":false,"fork":false,"pushed_at":"2023-05-23T13:34:57.000Z","size":4843,"stargazers_count":42,"open_issues_count":0,"forks_count":11,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-11-15T06:32:05.249Z","etag":null,"topics":["domain-adaptation","eccv-2020","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":"2020-07-29T12:22:57.000Z","updated_at":"2024-05-06T12:50:11.000Z","dependencies_parsed_at":"2024-01-12T07:24:36.469Z","dependency_job_id":"3f13d0f3-f759-4fd3-b336-ffe993563e30","html_url":"https://github.com/tim-learn/BA3US","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%2FBA3US","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tim-learn%2FBA3US/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tim-learn%2FBA3US/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tim-learn%2FBA3US/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tim-learn","download_url":"https://codeload.github.com/tim-learn/BA3US/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253085772,"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":["domain-adaptation","eccv-2020","transfer-learning"],"created_at":"2024-08-03T03:01:53.953Z","updated_at":"2025-05-08T14:33:05.875Z","avatar_url":"https://github.com/tim-learn.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"Code for our ECCV (2020) paper [**A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation**](https://arxiv.org/abs/2003.02541). \n\n![framework](framework.jpg)\n\n### Prerequisites:\n- python == 3.6.8\n- pytorch ==1.1.0\n- torchvision == 0.3.0\n- numpy, scipy, PIL, argparse, tqdm\n\n### Dataset:\n\n- Please manually download the datasets [Office](https://drive.google.com/file/d/0B4IapRTv9pJ1WGZVd1VDMmhwdlE/view), [Office-Home](https://drive.google.com/file/d/0B81rNlvomiwed0V1YUxQdC1uOTg/view), [ImageNet-Caltech](http://www.vision.caltech.edu/Image_Datasets/Caltech101/101_ObjectCategories.tar.gz) from the official websites, and modify the path of images in each '.txt' under the folder './data/'.\n- We adopt the same data protocol as [PADA](https://github.com/thuml/PADA/tree/master/pytorch/data).\n\n### Training:\n1. ##### Partial Domain Adaptation (PDA) on the Office-Home dataset [Art(s=0) -\u003e Clipart(t=1)]\n\t```python\n\tpython run_partial.py --s 0 --t 1 --dset office_home --net ResNet50 --cot_weight 1. --output run1 --gpu_id 0\n\t```\n\t\n2. ##### Partial Domain Adaptation (PDA) on the Office dataset [Amazon(s=0) -\u003e DSLR(t=1)]\n\t ```python\n   python run_partial.py --s 0 --t 1 --dset office --net ResNet50 --cot_weight 5. --output run1 --gpu_id 0\n   python run_partial.py --s 0 --t 1 --dset office --net VGG16 --cot_weight 5. --output run1 --gpu_id 0\n   ```\n   \n3. ##### Partial Domain Adaptation (PDA) on the ImageNet-Caltech dataset [ImageNet(s=0) -\u003e Caltech(t=1)]\n\t ```python\n   python run_partial.py --s 0 --t 1 --dset imagenet_caltech --net ResNet50 --cot_weight 5. --output run1 --gpu_id 0\n   ```\n\n\n### Citation\n\nIf you find this code useful for your research, please cite our paper\n\n\u003e @inproceedings{liang2020baus,  \n\u003e  \u0026nbsp; \u0026nbsp;  title={A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation},  \n\u003e  \u0026nbsp; \u0026nbsp;  author={Liang, Jian, and Wang, Yunbo, and Hu, Dapeng, and He, Ran and Feng, Jiashi},  \n\u003e  \u0026nbsp; \u0026nbsp;  booktitle={European Conference on Computer Vision (ECCV)},  \n\u003e  \u0026nbsp; \u0026nbsp;  pages={xx-xx},  \n\u003e  \u0026nbsp; \u0026nbsp;  month = {August},  \n\u003e  \u0026nbsp; \u0026nbsp;  year={2020}  \n\u003e }\n\n### Acknowledgement\n\nSome parts of this project are built based on the following open-source implementation \n- CDAN [https://github.com/thuml/CDAN/tree/master/pytorch](https://github.com/thuml/CDAN/tree/master/pytorch)\n- COT [https://github.com/henry8527/COT](https://github.com/henry8527/COT)\n\n### Contact\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)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftim-learn%2FBA3US","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftim-learn%2FBA3US","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftim-learn%2FBA3US/lists"}