{"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/understanding-bias-in-large-scale-visual","title":"Understanding Bias in Large-Scale Visual Datasets","arxiv_id":"2412.01876","date":"2024-12-02","proceeding":null,"authors":["Boya Zeng","Yida Yin","Zhuang Liu"],"abstract":"A recent study has shown that large-scale visual datasets are very biased: they can be easily classified by modern neural networks. However, the concrete forms of bias among these datasets remain unclear. In this study, we propose a framework to identify the unique visual attributes distinguishing these datasets. Our approach applies various transformations to extract semantic, structural, boundary, color, and frequency information from datasets, and assess how much each type of information reflects their bias. We further decompose their semantic bias with object-level analysis, and leverage natural language methods to generate detailed, open-ended descriptions of each dataset's characteristics. Our work aims to help researchers understand the bias in existing large-scale pre-training datasets, and build more diverse and representative ones in the future. Our project page and code are available at http://boyazeng.github.io/understand_bias .","url_abs":"https://arxiv.org/abs/2412.01876v1","url_pdf":"https://arxiv.org/pdf/2412.01876v1.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":"understanding-bias-in-large-scale-visual","repo_url":"https://github.com/boyazeng/understand_bias","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.01876","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01876"}},"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/boyazeng/understand_bias","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran_violates":1,"unverified":7},"by_repo_kind":{"official":{"samples":9,"ran":2,"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":9,"samples":[{"code_sha256_prefix":"f6be833ba409926f","entry":"pil_loader","repo":"boyazeng/understand_bias","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/boyazeng/understand_bias/blob/HEAD/dataset.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f6be833ba409926f"}},{"code_sha256_prefix":"ecf287c12bb06741","entry":"str2bool","repo":"boyazeng/understand_bias","repo_kind":"official","path":"transformations/trans_utils.py","file_url":"https://github.com/boyazeng/understand_bias/blob/HEAD/transformations/trans_utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ecf287c12bb06741"}},{"code_sha256_prefix":"9434ea7840290b34","entry":"IdealHighPass","repo":"boyazeng/understand_bias","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/boyazeng/understand_bias/blob/HEAD/dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9434ea7840290b34"}},{"code_sha256_prefix":"398bec59f7368690","entry":"IdealLowPass","repo":"boyazeng/understand_bias","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/boyazeng/understand_bias/blob/HEAD/dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"398bec59f7368690"}},{"code_sha256_prefix":"b700fb0a3496b255","entry":"cosine_scheduler","repo":"boyazeng/understand_bias","repo_kind":"official","path":"utils.py","file_url":"https://github.com/boyazeng/understand_bias/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b700fb0a3496b255"}},{"code_sha256_prefix":"d42ad965dffc78ee","entry":"create_aws_url","repo":"boyazeng/understand_bias","repo_kind":"official","path":"download_data/process_yfcc.py","file_url":"https://github.com/boyazeng/understand_bias/blob/HEAD/download_data/process_yfcc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d42ad965dffc78ee"}},{"code_sha256_prefix":"b7221aa032110c5e","entry":"create_flickr_url","repo":"boyazeng/understand_bias","repo_kind":"official","path":"download_data/process_yfcc.py","file_url":"https://github.com/boyazeng/understand_bias/blob/HEAD/download_data/process_yfcc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b7221aa032110c5e"}},{"code_sha256_prefix":"199223de2f9704cf","entry":"get_num_layer_for_convnext","repo":"boyazeng/understand_bias","repo_kind":"official","path":"optim_factory.py","file_url":"https://github.com/boyazeng/understand_bias/blob/HEAD/optim_factory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"199223de2f9704cf"}},{"code_sha256_prefix":"0ef0019514eaaa09","entry":"get_parameter_groups","repo":"boyazeng/understand_bias","repo_kind":"official","path":"optim_factory.py","file_url":"https://github.com/boyazeng/understand_bias/blob/HEAD/optim_factory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0ef0019514eaaa09"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}