{"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/vibe-a-tool-for-measuring-and-mitigating-bias","title":"REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets","arxiv_id":"2004.07999","date":"2020-04-16","proceeding":"ECCV 2020 8","authors":["Angelina Wang","Alexander Liu","Ryan Zhang","Anat Kleiman","Leslie Kim","Dora Zhao","Iroha Shirai","Arvind Narayanan","Olga Russakovsky"],"abstract":"Machine learning models are known to perpetuate and even amplify the biases present in the data. However, these data biases frequently do not become apparent until after the models are deployed. Our work tackles this issue and enables the preemptive analysis of large-scale datasets. REVISE (REvealing VIsual biaSEs) is a tool that assists in the investigation of a visual dataset, surfacing potential biases along three dimensions: (1) object-based, (2) person-based, and (3) geography-based. Object-based biases relate to the size, context, or diversity of the depicted objects. Person-based metrics focus on analyzing the portrayal of people within the dataset. Geography-based analyses consider the representation of different geographic locations. These three dimensions are deeply intertwined in how they interact to bias a dataset, and REVISE sheds light on this; the responsibility then lies with the user to consider the cultural and historical context, and to determine which of the revealed biases may be problematic. The tool further assists the user by suggesting actionable steps that may be taken to mitigate the revealed biases. Overall, the key aim of our work is to tackle the machine learning bias problem early in the pipeline. REVISE is available at https://github.com/princetonvisualai/revise-tool","url_abs":"https://arxiv.org/abs/2004.07999v4","url_pdf":"https://arxiv.org/pdf/2004.07999v4.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":"vibe-a-tool-for-measuring-and-mitigating-bias","repo_url":"https://github.com/princetonvisualai/revise-tool","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"vibe-a-tool-for-measuring-and-mitigating-bias","repo_url":"https://github.com/princetonvisualai/vibe-tool","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2004.07999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.07999"}},"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/princetonvisualai/revise-tool","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/princetonvisualai/vibe-tool","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"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":"a2c564ef3e28ab1d","entry":"bb_intersection_over_union","repo":"princetonvisualai/revise-tool","repo_kind":"official","path":"measurements/object_based.py","file_url":"https://github.com/princetonvisualai/revise-tool/blob/HEAD/measurements/object_based.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a2c564ef3e28ab1d"}},{"code_sha256_prefix":"801ebbc0eea48637","entry":"collate_fn","repo":"princetonvisualai/revise-tool","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/princetonvisualai/revise-tool/blob/HEAD/datasets.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":"801ebbc0eea48637"}},{"code_sha256_prefix":"33ffc831e94b6553","entry":"detect_face","repo":"princetonvisualai/revise-tool","repo_kind":"official","path":"measurements/attribute_based.py","file_url":"https://github.com/princetonvisualai/revise-tool/blob/HEAD/measurements/attribute_based.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":"33ffc831e94b6553"}},{"code_sha256_prefix":"a2da3d3e9594c4ed","entry":"project","repo":"princetonvisualai/revise-tool","repo_kind":"official","path":"measurements/prerun_analyzegeo.py","file_url":"https://github.com/princetonvisualai/revise-tool/blob/HEAD/measurements/prerun_analyzegeo.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":"a2da3d3e9594c4ed"}},{"code_sha256_prefix":"bed51f23c7b162eb","entry":"wilson","repo":"princetonvisualai/revise-tool","repo_kind":"official","path":"measurements/prerun_analyzegeo.py","file_url":"https://github.com/princetonvisualai/revise-tool/blob/HEAD/measurements/prerun_analyzegeo.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":"bed51f23c7b162eb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}