{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/rethinking-common-assumptions-to-mitigate","title":"Rethinking Common Assumptions to Mitigate Racial Bias in Face Recognition Datasets","arxiv_id":"2109.03229","date":"2021-09-07","proceeding":null,"authors":["Matthew Gwilliam","Srinidhi Hegde","Lade Tinubu","Alex Hanson"],"abstract":"Many existing works have made great strides towards reducing racial bias in face recognition. However, most of these methods attempt to rectify bias that manifests in models during training instead of directly addressing a major source of the bias, the dataset itself. Exceptions to this are BUPT-Balancedface/RFW and Fairface, but these works assume that primarily training on a single race or not racially balancing the dataset are inherently disadvantageous. We demonstrate that these assumptions are not necessarily valid. In our experiments, training on only African faces induced less bias than training on a balanced distribution of faces and distributions skewed to include more African faces produced more equitable models. We additionally notice that adding more images of existing identities to a dataset in place of adding new identities can lead to accuracy boosts across racial categories. Our code is available at https://github.com/j-alex-hanson/rethinking-race-face-datasets.","url_abs":"https://arxiv.org/abs/2109.03229v4","url_pdf":"https://arxiv.org/pdf/2109.03229v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"rethinking-common-assumptions-to-mitigate","repo_url":"https://github.com/j-alex-hanson/rethinking-race-face-datasets","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.03229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.03229"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/j-alex-hanson/rethinking-race-face-datasets","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"j-alex-hanson/rethinking-race-face-datasets","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/j-alex-hanson/rethinking-race-face-datasets/blob/HEAD/models/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"f4a3e5cb45da425c","entry":"compute_center_loss","repo":"j-alex-hanson/rethinking-race-face-datasets","repo_kind":"official","path":"models/center_loss.py","file_url":"https://github.com/j-alex-hanson/rethinking-race-face-datasets/blob/HEAD/models/center_loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f4a3e5cb45da425c"}},{"code_sha256_prefix":"d286d6ff7d7269a3","entry":"get_center_delta","repo":"j-alex-hanson/rethinking-race-face-datasets","repo_kind":"official","path":"models/center_loss.py","file_url":"https://github.com/j-alex-hanson/rethinking-race-face-datasets/blob/HEAD/models/center_loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d286d6ff7d7269a3"}},{"code_sha256_prefix":"5d6487504a24d080","entry":"resnet50_scratch_dag","repo":"j-alex-hanson/rethinking-race-face-datasets","repo_kind":"official","path":"models/vggface2.py","file_url":"https://github.com/j-alex-hanson/rethinking-race-face-datasets/blob/HEAD/models/vggface2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5d6487504a24d080"}},{"code_sha256_prefix":"3c67eb59a41f7c25","entry":"resnet_face18","repo":"j-alex-hanson/rethinking-race-face-datasets","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/j-alex-hanson/rethinking-race-face-datasets/blob/HEAD/models/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c67eb59a41f7c25"}},{"code_sha256_prefix":"f8578b2c78da1647","entry":"resnet_face50","repo":"j-alex-hanson/rethinking-race-face-datasets","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/j-alex-hanson/rethinking-race-face-datasets/blob/HEAD/models/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f8578b2c78da1647"}},{"code_sha256_prefix":"ddadafdacf7388fd","entry":"senet50_scratch_dag","repo":"j-alex-hanson/rethinking-race-face-datasets","repo_kind":"official","path":"models/vggface2.py","file_url":"https://github.com/j-alex-hanson/rethinking-race-face-datasets/blob/HEAD/models/vggface2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ddadafdacf7388fd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}