{"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/leveling-down-in-computer-vision-pareto","title":"Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers","arxiv_id":"2203.04913","date":"2022-03-09","proceeding":"CVPR 2022 1","authors":["Dominik Zietlow","Michael Lohaus","Guha Balakrishnan","Matthäus Kleindessner","Francesco Locatello","Bernhard Schölkopf","Chris Russell"],"abstract":"Algorithmic fairness is frequently motivated in terms of a trade-off in which overall performance is decreased so as to improve performance on disadvantaged groups where the algorithm would otherwise be less accurate. Contrary to this, we find that applying existing fairness approaches to computer vision improve fairness by degrading the performance of classifiers across all groups (with increased degradation on the best performing groups). Extending the bias-variance decomposition for classification to fairness, we theoretically explain why the majority of fairness classifiers designed for low capacity models should not be used in settings involving high-capacity models, a scenario common to computer vision. We corroborate this analysis with extensive experimental support that shows that many of the fairness heuristics used in computer vision also degrade performance on the most disadvantaged groups. Building on these insights, we propose an adaptive augmentation strategy that, uniquely, of all methods tested, improves performance for the disadvantaged groups.","url_abs":"https://arxiv.org/abs/2203.04913v2","url_pdf":"https://arxiv.org/pdf/2203.04913v2.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":"leveling-down-in-computer-vision-pareto","repo_url":"https://github.com/oxfordinternetinstitute/oxonfair","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"fairness","task_name":"Fairness"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.04913","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04913"}},"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/oxfordinternetinstitute/oxonfair","reach":null}],"summary":{"ran":2,"ran_fixture":6,"ran_honours":1,"unverified":3},"by_repo_kind":{"listed":{"samples":12,"ran":9,"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":"a798938602634eac","entry":"ScorerRequiresContPred","repo":"oxfordinternetinstitute/oxonfair","repo_kind":"listed","path":"src/oxonfair/learners/fair_frontier.py","file_url":"https://github.com/oxfordinternetinstitute/oxonfair/blob/HEAD/src/oxonfair/learners/fair_frontier.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a798938602634eac"}},{"code_sha256_prefix":"a0f7783ca53b47b4","entry":"inv_sigmoid","repo":"oxfordinternetinstitute/oxonfair","repo_kind":"listed","path":"src/oxonfair/learners/fair_frontier.py","file_url":"https://github.com/oxfordinternetinstitute/oxonfair/blob/HEAD/src/oxonfair/learners/fair_frontier.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a0f7783ca53b47b4"}},{"code_sha256_prefix":"77be5e697751a0e2","entry":"keep_front","repo":"oxfordinternetinstitute/oxonfair","repo_kind":"listed","path":"src/oxonfair/learners/fair_frontier.py","file_url":"https://github.com/oxfordinternetinstitute/oxonfair/blob/HEAD/src/oxonfair/learners/fair_frontier.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"77be5e697751a0e2"}},{"code_sha256_prefix":"564041634dc60656","entry":"linear_interpolate","repo":"oxfordinternetinstitute/oxonfair","repo_kind":"listed","path":"src/oxonfair/learners/fair_frontier.py","file_url":"https://github.com/oxfordinternetinstitute/oxonfair/blob/HEAD/src/oxonfair/learners/fair_frontier.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"564041634dc60656"}},{"code_sha256_prefix":"9f17ba1fc0db9998","entry":"make_finer_grid","repo":"oxfordinternetinstitute/oxonfair","repo_kind":"listed","path":"src/oxonfair/learners/fair_frontier.py","file_url":"https://github.com/oxfordinternetinstitute/oxonfair/blob/HEAD/src/oxonfair/learners/fair_frontier.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9f17ba1fc0db9998"}},{"code_sha256_prefix":"f6611e085260a40e","entry":"make_grid_arange","repo":"oxfordinternetinstitute/oxonfair","repo_kind":"listed","path":"src/oxonfair/learners/fair_frontier.py","file_url":"https://github.com/oxfordinternetinstitute/oxonfair/blob/HEAD/src/oxonfair/learners/fair_frontier.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f6611e085260a40e"}},{"code_sha256_prefix":"a63e6e87527b81a5","entry":"make_grid_between_points","repo":"oxfordinternetinstitute/oxonfair","repo_kind":"listed","path":"src/oxonfair/learners/fair_frontier.py","file_url":"https://github.com/oxfordinternetinstitute/oxonfair/blob/HEAD/src/oxonfair/learners/fair_frontier.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a63e6e87527b81a5"}},{"code_sha256_prefix":"b967ef0154b5c690","entry":"make_grid_linspace","repo":"oxfordinternetinstitute/oxonfair","repo_kind":"listed","path":"src/oxonfair/learners/fair_frontier.py","file_url":"https://github.com/oxfordinternetinstitute/oxonfair/blob/HEAD/src/oxonfair/learners/fair_frontier.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b967ef0154b5c690"}},{"code_sha256_prefix":"d05c71a4b943dde3","entry":"sigmoid","repo":"oxfordinternetinstitute/oxonfair","repo_kind":"listed","path":"src/oxonfair/learners/fair_frontier.py","file_url":"https://github.com/oxfordinternetinstitute/oxonfair/blob/HEAD/src/oxonfair/learners/fair_frontier.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d05c71a4b943dde3"}},{"code_sha256_prefix":"3db1bcc322e1063f","entry":"build_coarse_to_fine_front","repo":"oxfordinternetinstitute/oxonfair","repo_kind":"listed","path":"src/oxonfair/learners/fair_frontier.py","file_url":"https://github.com/oxfordinternetinstitute/oxonfair/blob/HEAD/src/oxonfair/learners/fair_frontier.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3db1bcc322e1063f"}},{"code_sha256_prefix":"da52ff2f71de7630","entry":"compute_metrics","repo":"oxfordinternetinstitute/oxonfair","repo_kind":"listed","path":"src/oxonfair/learners/fair_frontier.py","file_url":"https://github.com/oxfordinternetinstitute/oxonfair/blob/HEAD/src/oxonfair/learners/fair_frontier.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"da52ff2f71de7630"}},{"code_sha256_prefix":"9b5a3d2ae57a9889","entry":"front_from_weights","repo":"oxfordinternetinstitute/oxonfair","repo_kind":"listed","path":"src/oxonfair/learners/fair_frontier.py","file_url":"https://github.com/oxfordinternetinstitute/oxonfair/blob/HEAD/src/oxonfair/learners/fair_frontier.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9b5a3d2ae57a9889"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}