{"id":23136692,"url":"https://github.com/naoto0804/cross-domain-detection","last_synced_at":"2025-04-05T08:09:29.293Z","repository":{"id":50305594,"uuid":"124737291","full_name":"naoto0804/cross-domain-detection","owner":"naoto0804","description":"Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation [Inoue+, CVPR2018].","archived":false,"fork":false,"pushed_at":"2024-03-16T05:41:18.000Z","size":1931,"stargazers_count":427,"open_issues_count":7,"forks_count":77,"subscribers_count":10,"default_branch":"master","last_synced_at":"2025-03-29T07:09:17.051Z","etag":null,"topics":["chainer","cross-domain","domain-adaptation","object-detection","weakly-supervised-learning"],"latest_commit_sha":null,"homepage":"https://naoto0804.github.io/cross_domain_detection/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/naoto0804.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2018-03-11T08:28:12.000Z","updated_at":"2025-03-03T12:40:40.000Z","dependencies_parsed_at":"2024-12-17T12:38:52.411Z","dependency_job_id":null,"html_url":"https://github.com/naoto0804/cross-domain-detection","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/naoto0804%2Fcross-domain-detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/naoto0804%2Fcross-domain-detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/naoto0804%2Fcross-domain-detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/naoto0804%2Fcross-domain-detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/naoto0804","download_url":"https://codeload.github.com/naoto0804/cross-domain-detection/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247305935,"owners_count":20917208,"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":["chainer","cross-domain","domain-adaptation","object-detection","weakly-supervised-learning"],"created_at":"2024-12-17T12:25:30.186Z","updated_at":"2025-04-05T08:09:29.272Z","avatar_url":"https://github.com/naoto0804.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation \n\nThis page is for the [paper](http://openaccess.thecvf.com/content_cvpr_2018/html/Inoue_Cross-Domain_Weakly-Supervised_Object_CVPR_2018_paper.html) appeared in CVPR2018.\nYou can also find [project page](https://naoto0804.github.io/cross_domain_detection/) for the paper.\n\nHere is the example of our results in watercolor images.\n\n![fig](dets_watercolor.png)\n\n## Requirements\n- Python 3.5+\n- Chainer 3.0+\n- ChainerCV 0.8\n- Cupy 2.0+\n- OpenCV 3+\n- Matplotlib\n\nPlease install all the libraries. We recommend `pip install -r requirements.txt`.\n\n## Download models\nPlease go to both `models` and `datasets` directory and follow the instructions.\n\n## Usage\nFor more details about arguments, please refer to `-h` option or the actual codes.\n\n### Demo using trained models\n```\npython demo.py input/watercolor_142090457.jpg output.jpg --gpu 0 --load models/watercolor_dt_pl_ssd300\n```\n\n### Evaluation of trained models\n```\npython eval_model.py --root datasets/clipart --data_type clipart --det_type ssd300 --gpu 0 --load models/clipart_dt_pl_ssd300\n```\n\n### Training using clean instance-level annotations (ideal case)\n```\npython train_model.py --root datasets/clipart --subset train --result result --det_type ssd300 --data_type clipart --gpu 0\n```\n\n### Training using virtually created instance-level annotations\n\nRest of this section shows examples for experiments in `clipart` dataset.\n\n1. (Preprocess): please follow instructions in `./datasets/README.md` to create folders.\n\n2. Domain transfer (DT) step\n\n    1. `python train_model.py --root datasets/dt_clipart/VOC2007 --root datasets/dt_clipart/VOC2012 --subset trainval --result result/dt_clipart --det_type ssd300 --data_type clipart --gpu 0 --max_iter 500 --eval_root datasets/clipart`\n    \n    We provide models obtained in this step at `./models`.\n\n3. Pseudo labeling (PL) step\n    1. `python pseudo_label.py --root datasets/clipart --data_type clipart --det_type ssd300 --gpu 0 --load models/clipart_dt_ssd300 --result datasets/dt_pl_clipart`\n    2. `python train_model.py --root datasets/dt_pl_clipart --subset train --result result/dt_pl_clipart --det_type ssd300 --data_type clipart --gpu 0 --load models/clipart_dt_ssd300 --eval_root datasets/clipart`\n\n### Citation\n\nIf you find this code or dataset useful for your research, please cite our paper:\n\n```\n@inproceedings{inoue2018cross,\n  title={Cross-domain weakly-supervised object detection through progressive domain adaptation},\n  author={Inoue, Naoto and Furuta, Ryosuke and Yamasaki, Toshihiko and Aizawa, Kiyoharu},\n  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},\n  pages={5001--5009},\n  year={2018}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnaoto0804%2Fcross-domain-detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnaoto0804%2Fcross-domain-detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnaoto0804%2Fcross-domain-detection/lists"}