{"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/sebra-debiasing-through-self-guided-bias","title":"Sebra: Debiasing Through Self-Guided Bias Ranking","arxiv_id":"2501.18277","date":"2025-01-30","proceeding":null,"authors":["Adarsh Kappiyath","Abhra Chaudhuri","Ajay Jaiswal","Ziquan Liu","Yunpeng Li","Xiatian Zhu","Lu Yin"],"abstract":"Ranking samples by fine-grained estimates of spuriosity (the degree to which spurious cues are present) has recently been shown to significantly benefit bias mitigation, over the traditional binary biased-\\textit{vs}-unbiased partitioning of train sets. However, this spuriosity ranking comes with the requirement of human supervision. In this paper, we propose a debiasing framework based on our novel \\ul{Se}lf-Guided \\ul{B}ias \\ul{Ra}nking (\\emph{Sebra}), that mitigates biases (spurious correlations) via an automatic ranking of data points by spuriosity within their respective classes. Sebra leverages a key local symmetry in Empirical Risk Minimization (ERM) training -- the ease of learning a sample via ERM inversely correlates with its spuriousity; the fewer spurious correlations a sample exhibits, the harder it is to learn, and vice versa. However, globally across iterations, ERM tends to deviate from this symmetry. Sebra dynamically steers ERM to correct this deviation, facilitating the sequential learning of attributes in increasing order of difficulty, \\ie, decreasing order of spuriosity. As a result, the sequence in which Sebra learns samples naturally provides spuriousity rankings. We use the resulting fine-grained bias characterization in a contrastive learning framework to mitigate biases from multiple sources. Extensive experiments show that Sebra consistently outperforms previous state-of-the-art unsupervised debiasing techniques across multiple standard benchmarks, including UrbanCars, BAR, CelebA, and ImageNet-1K. Code, pre-trained models, and training logs are available at https://kadarsh22.github.io/sebra_iclr25/.","url_abs":"https://arxiv.org/abs/2501.18277v1","url_pdf":"https://arxiv.org/pdf/2501.18277v1.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":"sebra-debiasing-through-self-guided-bias","repo_url":"https://github.com/kadarsh22/Sebra","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2501.18277","atlas_url":"https://app.syntology.ai/?focus=2501.18277","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.18277"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/kadarsh22/Sebra","reach":null}],"summary":{"ran":5,"ran_draft_wrong":2,"ran_fixture":1,"unverified":3},"by_repo_kind":{"official":{"samples":11,"ran":8,"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":11,"samples":[{"code_sha256_prefix":"3c1e74bdaf82c34d","entry":"AverageMeter","repo":"kadarsh22/Sebra","repo_kind":"official","path":"bar_trainers/sebra.py","file_url":"https://github.com/kadarsh22/Sebra/blob/HEAD/bar_trainers/sebra.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3c1e74bdaf82c34d"}},{"code_sha256_prefix":"1541e6d73cae1e23","entry":"BAR","repo":"kadarsh22/Sebra","repo_kind":"official","path":"bar_trainers/sebra.py","file_url":"https://github.com/kadarsh22/Sebra/blob/HEAD/bar_trainers/sebra.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1541e6d73cae1e23"}},{"code_sha256_prefix":"d2d39ea83e16d858","entry":"MLP","repo":"kadarsh22/Sebra","repo_kind":"official","path":"bar_trainers/sebra.py","file_url":"https://github.com/kadarsh22/Sebra/blob/HEAD/bar_trainers/sebra.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d2d39ea83e16d858"}},{"code_sha256_prefix":"76310f9e6e845032","entry":"SupervisedContrastiveLoss","repo":"kadarsh22/Sebra","repo_kind":"official","path":"bar_trainers/sebra.py","file_url":"https://github.com/kadarsh22/Sebra/blob/HEAD/bar_trainers/sebra.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"76310f9e6e845032"}},{"code_sha256_prefix":"d86f50d7e99c376a","entry":"UpweightedTrainingLoss","repo":"kadarsh22/Sebra","repo_kind":"official","path":"bar_trainers/sebra.py","file_url":"https://github.com/kadarsh22/Sebra/blob/HEAD/bar_trainers/sebra.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d86f50d7e99c376a"}},{"code_sha256_prefix":"2194ec58c39d65e1","entry":"add_prefix_dict","repo":"kadarsh22/Sebra","repo_kind":"official","path":"bar_trainers/sebra.py","file_url":"https://github.com/kadarsh22/Sebra/blob/HEAD/bar_trainers/sebra.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2194ec58c39d65e1"}},{"code_sha256_prefix":"fbdf12a7504f8ac4","entry":"collate_fn","repo":"kadarsh22/Sebra","repo_kind":"official","path":"bar_trainers/sebra.py","file_url":"https://github.com/kadarsh22/Sebra/blob/HEAD/bar_trainers/sebra.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fbdf12a7504f8ac4"}},{"code_sha256_prefix":"2ac8bdd19ac77073","entry":"get_model_and_transforms","repo":"kadarsh22/Sebra","repo_kind":"official","path":"bar_trainers/sebra.py","file_url":"https://github.com/kadarsh22/Sebra/blob/HEAD/bar_trainers/sebra.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2ac8bdd19ac77073"}},{"code_sha256_prefix":"e74b9abb8ae82d42","entry":"BaseActionTrainer","repo":"kadarsh22/Sebra","repo_kind":"official","path":"bar_trainers/sebra.py","file_url":"https://github.com/kadarsh22/Sebra/blob/HEAD/bar_trainers/sebra.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":"e74b9abb8ae82d42"}},{"code_sha256_prefix":"c42bde612b7e0df4","entry":"Trainer","repo":"kadarsh22/Sebra","repo_kind":"official","path":"bar_trainers/sebra.py","file_url":"https://github.com/kadarsh22/Sebra/blob/HEAD/bar_trainers/sebra.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":"c42bde612b7e0df4"}},{"code_sha256_prefix":"99ce977f396cefaa","entry":"get_action_dataset_train_test","repo":"kadarsh22/Sebra","repo_kind":"official","path":"bar_trainers/sebra.py","file_url":"https://github.com/kadarsh22/Sebra/blob/HEAD/bar_trainers/sebra.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":"99ce977f396cefaa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}