{"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/generalized-jensen-shannon-divergence-loss","title":"Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels","arxiv_id":"2105.04522","date":"2021-05-10","proceeding":"NeurIPS 2021 12","authors":["Erik Englesson","Hossein Azizpour"],"abstract":"Prior works have found it beneficial to combine provably noise-robust loss functions e.g., mean absolute error (MAE) with standard categorical loss function e.g. cross entropy (CE) to improve their learnability. Here, we propose to use Jensen-Shannon divergence as a noise-robust loss function and show that it interestingly interpolate between CE and MAE with a controllable mixing parameter. Furthermore, we make a crucial observation that CE exhibit lower consistency around noisy data points. Based on this observation, we adopt a generalized version of the Jensen-Shannon divergence for multiple distributions to encourage consistency around data points. Using this loss function, we show state-of-the-art results on both synthetic (CIFAR), and real-world (e.g., WebVision) noise with varying noise rates.","url_abs":"https://arxiv.org/abs/2105.04522v4","url_pdf":"https://arxiv.org/pdf/2105.04522v4.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":"generalized-jensen-shannon-divergence-loss","repo_url":"https://github.com/erikenglesson/gjs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"learning-with-noisy-labels","task_name":"Learning with noisy labels"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-mini-webvision-1-0","task":"Image Classification","dataset":"mini WebVision 1.0","model":"GJS (ResNet-50)","rank_in_archive_order":18,"of":47,"metrics":{"ImageNet Top-1 Accuracy":"75.50","ImageNet Top-5 Accuracy":"91.27","Top-1 Accuracy":"79.28","Top-5 Accuracy":"91.22"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2105.04522","atlas_url":"https://app.syntology.ai/?focus=2105.04522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.04522"}},"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/erikenglesson/gjs","reach":null}],"summary":{"ran":1,"ran_draft_wrong":2,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":5,"samples":[{"code_sha256_prefix":"411608e7efd42f94","entry":"JensenShannonDivergenceWeightedCustom","repo":"erikenglesson/gjs","repo_kind":"official","path":"losses.py","file_url":"https://github.com/erikenglesson/gjs/blob/HEAD/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"411608e7efd42f94"}},{"code_sha256_prefix":"f07ad940a29ae3c5","entry":"custom_ce","repo":"erikenglesson/gjs","repo_kind":"official","path":"losses.py","file_url":"https://github.com/erikenglesson/gjs/blob/HEAD/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f07ad940a29ae3c5"}},{"code_sha256_prefix":"b7e66a91c19383df","entry":"custom_kl_div","repo":"erikenglesson/gjs","repo_kind":"official","path":"losses.py","file_url":"https://github.com/erikenglesson/gjs/blob/HEAD/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b7e66a91c19383df"}},{"code_sha256_prefix":"f508a1f840aee873","entry":"custom_kl_div","repo":"erikenglesson/gjs","repo_kind":"official","path":"losses.py","file_url":"https://github.com/erikenglesson/gjs/blob/HEAD/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f508a1f840aee873"}},{"code_sha256_prefix":"c5746d47232aa0b1","entry":"get_criterion","repo":"erikenglesson/gjs","repo_kind":"official","path":"losses.py","file_url":"https://github.com/erikenglesson/gjs/blob/HEAD/losses.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":"c5746d47232aa0b1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}