{"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-generalized-label-smoothing","title":"To Smooth or Not? When Label Smoothing Meets Noisy Labels","arxiv_id":"2106.04149","date":"2021-06-08","proceeding":null,"authors":["Jiaheng Wei","Hangyu Liu","Tongliang Liu","Gang Niu","Masashi Sugiyama","Yang Liu"],"abstract":"Label smoothing (LS) is an arising learning paradigm that uses the positively weighted average of both the hard training labels and uniformly distributed soft labels. It was shown that LS serves as a regularizer for training data with hard labels and therefore improves the generalization of the model. Later it was reported LS even helps with improving robustness when learning with noisy labels. However, we observed that the advantage of LS vanishes when we operate in a high label noise regime. Intuitively speaking, this is due to the increased entropy of $\\mathbb{P}(\\text{noisy label}|X)$ when the noise rate is high, in which case, further applying LS tends to \"over-smooth\" the estimated posterior. We proceeded to discover that several learning-with-noisy-labels solutions in the literature instead relate more closely to negative/not label smoothing (NLS), which acts counter to LS and defines as using a negative weight to combine the hard and soft labels! We provide understandings for the properties of LS and NLS when learning with noisy labels. Among other established properties, we theoretically show NLS is considered more beneficial when the label noise rates are high. We provide extensive experimental results on multiple benchmarks to support our findings too. Code is publicly available at https://github.com/UCSC-REAL/negative-label-smoothing.","url_abs":"https://arxiv.org/abs/2106.04149v6","url_pdf":"https://arxiv.org/pdf/2106.04149v6.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-generalized-label-smoothing","repo_url":"https://github.com/ucsc-real/negative-label-smoothing","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":[{"method_slug":"label-smoothing","method_name":"Label Smoothing"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-clothing1m","task":"Image Classification","dataset":"Clothing1M","model":"Negative Label Smoothing (NLS)","rank_in_archive_order":21,"of":51,"metrics":{"Accuracy":"74.24%"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-100n","task":"Learning with noisy labels","dataset":"CIFAR-100N","model":"Negative-LS","rank_in_archive_order":13,"of":24,"metrics":{"Accuracy (mean)":"58.59"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n","task":"Learning with noisy labels","dataset":"CIFAR-10N-Aggregate","model":"Negative-LS","rank_in_archive_order":13,"of":26,"metrics":{"Accuracy (mean)":"91.97"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n-1","task":"Learning with noisy labels","dataset":"CIFAR-10N-Random1","model":"Negative-LS","rank_in_archive_order":13,"of":24,"metrics":{"Accuracy (mean)":"90.29"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n-2","task":"Learning with noisy labels","dataset":"CIFAR-10N-Random2","model":"Negative-LS","rank_in_archive_order":10,"of":23,"metrics":{"Accuracy (mean)":"90.37"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n-3","task":"Learning with noisy labels","dataset":"CIFAR-10N-Random3","model":"Negative-LS","rank_in_archive_order":10,"of":23,"metrics":{"Accuracy (mean)":"90.13"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2106.04149","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04149"}},"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/ucsc-real/negative-label-smoothing","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"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":3,"samples":[{"code_sha256_prefix":"f9a6b87cd831fd0f","entry":"det_acc","repo":"UCSC-REAL/negative-label-smoothing","repo_kind":"official","path":"loss.py","file_url":"https://github.com/UCSC-REAL/negative-label-smoothing/blob/HEAD/loss.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":"f9a6b87cd831fd0f"}},{"code_sha256_prefix":"c728b54b52ba6b19","entry":"loss_gls","repo":"UCSC-REAL/negative-label-smoothing","repo_kind":"official","path":"loss.py","file_url":"https://github.com/UCSC-REAL/negative-label-smoothing/blob/HEAD/loss.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":"c728b54b52ba6b19"}},{"code_sha256_prefix":"32a3f3764f3ca474","entry":"loss_gls","repo":"ucsc-real/negative-label-smoothing","repo_kind":"official","path":"loss.py","file_url":"https://github.com/ucsc-real/negative-label-smoothing/blob/HEAD/loss.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":"32a3f3764f3ca474"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}