{"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/unsupervised-label-noise-modeling-and-loss","title":"Unsupervised Label Noise Modeling and Loss Correction","arxiv_id":"1904.11238","date":"2019-04-25","proceeding":null,"authors":["Eric Arazo","Diego Ortego","Paul Albert","Noel E. O'Connor","Kevin McGuinness"],"abstract":"Despite being robust to small amounts of label noise, convolutional neural networks trained with stochastic gradient methods have been shown to easily fit random labels. When there are a mixture of correct and mislabelled targets, networks tend to fit the former before the latter. This suggests using a suitable two-component mixture model as an unsupervised generative model of sample loss values during training to allow online estimation of the probability that a sample is mislabelled. Specifically, we propose a beta mixture to estimate this probability and correct the loss by relying on the network prediction (the so-called bootstrapping loss). We further adapt mixup augmentation to drive our approach a step further. Experiments on CIFAR-10/100 and TinyImageNet demonstrate a robustness to label noise that substantially outperforms recent state-of-the-art. Source code is available at https://git.io/fjsvE","url_abs":"https://arxiv.org/abs/1904.11238v2","url_pdf":"https://arxiv.org/pdf/1904.11238v2.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":"unsupervised-label-noise-modeling-and-loss","repo_url":"https://github.com/PaulAlbert31/LabelNoiseCorrection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"unsupervised-label-noise-modeling-and-loss","repo_url":"https://github.com/maxwell0027/pefat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"mixup","method_name":"Mixup"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-clothing1m","task":"Image Classification","dataset":"Clothing1M","model":"DY","rank_in_archive_order":45,"of":51,"metrics":{"Accuracy":"71%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.11238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.11238"}},"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/PaulAlbert31/LabelNoiseCorrection","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/maxwell0027/pefat","reach":{"status":"ok"}}],"summary":{"ran_honours":2,"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":3,"ran":3,"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":"2b9e8038de494dd6","entry":"add_noise_cifar_wo","repo":"PaulAlbert31/LabelNoiseCorrection","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/PaulAlbert31/LabelNoiseCorrection/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b9e8038de494dd6"}},{"code_sha256_prefix":"fbf3de45fc35f1c3","entry":"get_data_cifar","repo":"PaulAlbert31/LabelNoiseCorrection","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/PaulAlbert31/LabelNoiseCorrection/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fbf3de45fc35f1c3"}},{"code_sha256_prefix":"3dc10323e09ee8c4","entry":"get_data_cifar_2","repo":"PaulAlbert31/LabelNoiseCorrection","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/PaulAlbert31/LabelNoiseCorrection/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3dc10323e09ee8c4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}