{"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/learning-from-failure-training-debiased","title":"Learning from Failure: Training Debiased Classifier from Biased Classifier","arxiv_id":"2007.02561","date":"2020-07-06","proceeding":null,"authors":["Junhyun Nam","Hyuntak Cha","Sungsoo Ahn","Jaeho Lee","Jinwoo Shin"],"abstract":"Neural networks often learn to make predictions that overly rely on spurious correlation existing in the dataset, which causes the model to be biased. While previous work tackles this issue by using explicit labeling on the spuriously correlated attributes or presuming a particular bias type, we instead utilize a cheaper, yet generic form of human knowledge, which can be widely applicable to various types of bias. We first observe that neural networks learn to rely on the spurious correlation only when it is \"easier\" to learn than the desired knowledge, and such reliance is most prominent during the early phase of training. Based on the observations, we propose a failure-based debiasing scheme by training a pair of neural networks simultaneously. Our main idea is twofold; (a) we intentionally train the first network to be biased by repeatedly amplifying its \"prejudice\", and (b) we debias the training of the second network by focusing on samples that go against the prejudice of the biased network in (a). Extensive experiments demonstrate that our method significantly improves the training of the network against various types of biases in both synthetic and real-world datasets. Surprisingly, our framework even occasionally outperforms the debiasing methods requiring explicit supervision of the spuriously correlated attributes.","url_abs":"https://arxiv.org/abs/2007.02561v2","url_pdf":"https://arxiv.org/pdf/2007.02561v2.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":"learning-from-failure-training-debiased","repo_url":"https://github.com/alinlab/BAR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"learning-from-failure-training-debiased","repo_url":"https://github.com/alinlab/LfF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"facial-attribute-classification","task_name":"Facial Attribute Classification"},{"task_slug":"out-of-distribution-generalization","task_name":"Out-of-Distribution Generalization"}],"methods":[],"datasets_introduced":[{"slug":"bar","name":"BAR","full_name":"Biased Action Recognition"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-recognition-on-bar","task":"Action Recognition","dataset":"BAR","model":"LfF","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"62.98"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.02561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.02561"}},"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/alinlab/LfF","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alinlab/BAR","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"d1527cbc2296cba6","entry":"make_attr_labels","repo":"alinlab/LfF","repo_kind":"listed","path":"make_dataset.py","file_url":"https://github.com/alinlab/LfF/blob/HEAD/make_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d1527cbc2296cba6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}