{"id":13576185,"url":"https://github.com/bupt-ai-cz/PGDF","last_synced_at":"2025-04-05T05:31:05.103Z","repository":{"id":108962651,"uuid":"434514773","full_name":"bupt-ai-cz/PGDF","owner":"bupt-ai-cz","description":"Sample Prior Guided Robust Model Learning to Suppress Noisy Labels ","archived":false,"fork":false,"pushed_at":"2022-03-18T08:43:24.000Z","size":34,"stargazers_count":31,"open_issues_count":0,"forks_count":5,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-11-05T12:33:07.075Z","etag":null,"topics":["computer-vision","deep-learning","image-classification","noisy-labels"],"latest_commit_sha":null,"homepage":"","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/bupt-ai-cz.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":"2021-12-03T08:06:38.000Z","updated_at":"2024-06-23T00:24:12.000Z","dependencies_parsed_at":null,"dependency_job_id":"2ade6d77-5a1b-4971-9213-f39a31149876","html_url":"https://github.com/bupt-ai-cz/PGDF","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/bupt-ai-cz%2FPGDF","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bupt-ai-cz%2FPGDF/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bupt-ai-cz%2FPGDF/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bupt-ai-cz%2FPGDF/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bupt-ai-cz","download_url":"https://codeload.github.com/bupt-ai-cz/PGDF/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247294174,"owners_count":20915332,"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":["computer-vision","deep-learning","image-classification","noisy-labels"],"created_at":"2024-08-01T15:01:07.780Z","updated_at":"2025-04-05T05:31:00.083Z","avatar_url":"https://github.com/bupt-ai-cz.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# PGDF ![visitors](https://visitor-badge.glitch.me/badge?page_id=bupt-ai-cz.PGDF)\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/sample-prior-guided-robust-model-learning-to/image-classification-on-mini-webvision-1-0)](https://paperswithcode.com/sota/image-classification-on-mini-webvision-1-0?p=sample-prior-guided-robust-model-learning-to)  [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/sample-prior-guided-robust-model-learning-to/image-classification-on-clothing1m)](https://paperswithcode.com/sota/image-classification-on-clothing1m?p=sample-prior-guided-robust-model-learning-to)  [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/sample-prior-guided-robust-model-learning-to/image-classification-on-cifar-10-with-noisy)](https://paperswithcode.com/sota/image-classification-on-cifar-10-with-noisy?p=sample-prior-guided-robust-model-learning-to)\n\nThis repo is the official implementation of our paper [\"Sample Prior Guided Robust Model Learning to Suppress Noisy Labels\n\"](https://arxiv.org/abs/2112.01197).\n\n## Citation\nIf you use this code for your research, please cite our paper [\"Sample Prior Guided Robust Model Learning to Suppress Noisy Labels\n\"](https://arxiv.org/abs/2112.01197).\n\n\n```\n@misc{chen2022sample,\n      title={Sample Prior Guided Robust Model Learning to Suppress Noisy Labels}, \n      author={Wenkai Chen and Chuang Zhu and Yi Chen and Mengting Li and Tiejun Huang},\n      year={2022},\n      eprint={2112.01197},\n      archivePrefix={arXiv},\n      primaryClass={cs.CV}\n}\n```\n\n\n## Training\nTake CIFAR-10 with 50% symmetric noise as an example:\n\nFirst, please modify the `data_path` in ``presets.json`` to indicate the location of your dataset.\n\nThen, run\n```bash\npython train_cifar_getPrior.py --preset c10.50sym\n```\nto get the prior knowledge. Related files will be saved in ``checkpoints/c10/50sym/saved/``.\n\nNext, run\n```bash\npython train_cifar.py --preset c10.50sym\n```\nfor the subsequent training process.\n\n``c10`` means CIFAR-10, ``50sym`` means 50% symmetric noise.  \nSimilarly, if you want to take experiment on CIFAR-100 with 20% symmetric noise, you can use the command:\n```bash\npython train_cifar_getPrior.py --preset c100.20sym\n```\n```bash\npython train_cifar.py --preset c100.20sym\n```\n\n\n\n## Contact\n\nWenkai Chen\n- email: wkchen@bupt.edu.cn\n- wechat: cwkyiyi\n\nChuang Zhu\n- email: czhu@bupt.edu.cn\n- homepage: https://teacher.bupt.edu.cn/zhuchuang/zh_CN/index.htm\n\nIf you have any question about the code and data, please contact us directly.\n\n\n## Additional Info\nThe (basic) semi-supervised learning part of our code is borrow from [the official DM-AugDesc implementation](https://github.com/KentoNishi/Augmentation-for-LNL/).\n\nSince this paper has not yet been published, we only release part of the experimental code. We will release all the experimental codes after this paper is accepted by a conference.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbupt-ai-cz%2FPGDF","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbupt-ai-cz%2FPGDF","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbupt-ai-cz%2FPGDF/lists"}