{"id":21886472,"url":"https://github.com/kurtisdavid/metaorthogonalization","last_synced_at":"2025-08-15T22:15:43.200Z","repository":{"id":89182896,"uuid":"312950274","full_name":"kurtisdavid/MetaOrthogonalization","owner":"kurtisdavid","description":"Code for Debiasing Convolutional Neural Networks via Meta Orthogonalization (NeuRIPS 2020 AFCI Workshop).  ","archived":false,"fork":false,"pushed_at":"2020-12-07T01:14:14.000Z","size":526,"stargazers_count":4,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-31T13:31:13.738Z","etag":null,"topics":["computer-vision","deep-learning","fairness-ml","interpretability","machine-learning"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2011.07453","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/kurtisdavid.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":"2020-11-15T03:29:19.000Z","updated_at":"2022-08-24T20:02:43.000Z","dependencies_parsed_at":"2023-03-01T10:00:10.206Z","dependency_job_id":null,"html_url":"https://github.com/kurtisdavid/MetaOrthogonalization","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/kurtisdavid/MetaOrthogonalization","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kurtisdavid%2FMetaOrthogonalization","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kurtisdavid%2FMetaOrthogonalization/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kurtisdavid%2FMetaOrthogonalization/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kurtisdavid%2FMetaOrthogonalization/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kurtisdavid","download_url":"https://codeload.github.com/kurtisdavid/MetaOrthogonalization/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kurtisdavid%2FMetaOrthogonalization/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":270637485,"owners_count":24620426,"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":"2025-08-15T02:00:12.559Z","response_time":110,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","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","deep-learning","fairness-ml","interpretability","machine-learning"],"created_at":"2024-11-28T10:36:01.972Z","updated_at":"2025-08-15T22:15:43.139Z","avatar_url":"https://github.com/kurtisdavid.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MetaOrthogonalization \u003cbr\u003e\n[Kurtis Evan David](https://kurtisdavid.github.io), \n[Qiang Liu](https://www.cs.utexas.edu/~lqiang/), \n[Ruth Fong](https://ruthcfong.github.io/)\n## [[Paper]](https://arxiv.org/abs/2011.07453)\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"metaortho_figure.png\" /\u003e\n\u003c/div\u003e\n\n## Citation\n```bibtex\n@article{david2020debiasing,\n      title={Debiasing Convolutional Neural Networks via Meta Orthogonalization},\n      author={Kurtis Evan David and Qiang Liu and Ruth Fong},\n      year={2020},\n      journal={arXiv preprint arXiv:2011.07453},\n}\n```\n\n## Overview\nThis is the official implementation of Meta Orthogonalization in [PyTorch](https://pytorch.org/).\nOur main idea is to debias convolutional networks by making downstream concepts be orthogonal to a learned bias direction. \nThis is directly inspired by similar methods in NLP by [Bolukbasi et al. (2016)](https://arxiv.org/abs/1607.06520).\n\n## Required Libraries\nTo successfully run the code in this repo, make sure you have the following libraries installed:\n* PyTorch 1.5.0 (CUDA 10.1)\n* [higher](https://github.com/facebookresearch/higher)\n* [bam](https://github.com/google-research-datasets/bam)\n\n\n## Acknowledgement\nWe would like to thank Tianlu Wang for collaborating and providing more details with [adversarial debiasing](https://arxiv.org/abs/1811.08489) and their models. Please also cite their paper if you use this codebase for COCO, as we use theirs provided [here](https://github.com/uvavision/Balanced-Datasets-Are-Not-Enough).\n\n## Contact\nIf you have any questions, please contact us through kurtis.e.david(at)gmail.com.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkurtisdavid%2Fmetaorthogonalization","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkurtisdavid%2Fmetaorthogonalization","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkurtisdavid%2Fmetaorthogonalization/lists"}