{"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/delving-deep-into-label-smoothing","title":"Delving Deep into Label Smoothing","arxiv_id":"2011.12562","date":"2020-11-25","proceeding":null,"authors":["Chang-Bin Zhang","Peng-Tao Jiang","Qibin Hou","Yunchao Wei","Qi Han","Zhen Li","Ming-Ming Cheng"],"abstract":"Label smoothing is an effective regularization tool for deep neural networks (DNNs), which generates soft labels by applying a weighted average between the uniform distribution and the hard label. It is often used to reduce the overfitting problem of training DNNs and further improve classification performance. In this paper, we aim to investigate how to generate more reliable soft labels. We present an Online Label Smoothing (OLS) strategy, which generates soft labels based on the statistics of the model prediction for the target category. The proposed OLS constructs a more reasonable probability distribution between the target categories and non-target categories to supervise DNNs. Experiments demonstrate that based on the same classification models, the proposed approach can effectively improve the classification performance on CIFAR-100, ImageNet, and fine-grained datasets. Additionally, the proposed method can significantly improve the robustness of DNN models to noisy labels compared to current label smoothing approaches.","url_abs":"https://arxiv.org/abs/2011.12562v2","url_pdf":"https://arxiv.org/pdf/2011.12562v2.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":"delving-deep-into-label-smoothing","repo_url":"https://github.com/zhangchbin/OnlineLabelSmoothing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"delving-deep-into-label-smoothing","repo_url":"https://github.com/ankandrew/online-label-smoothing-pt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[{"method_slug":"label-smoothing","method_name":"Label Smoothing"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2011.12562","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.12562"}},"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/ankandrew/online-label-smoothing-pt","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhangchbin/OnlineLabelSmoothing","reach":null}],"summary":{"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"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":0,"samples":[{"code_sha256_prefix":"e96e8e4fb8100d26","entry":"get_learning_rate","repo":"zhangchbin/OnlineLabelSmoothing","repo_kind":"official","path":"cifar/scripts/train_cifar_all_methods.py","file_url":"https://github.com/zhangchbin/OnlineLabelSmoothing/blob/HEAD/cifar/scripts/train_cifar_all_methods.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":"e96e8e4fb8100d26"}},{"code_sha256_prefix":"6b88a61420e304e7","entry":"accuracy","repo":"zhangchbin/OnlineLabelSmoothing","repo_kind":"official","path":"cifar/scripts/train_cifar_all_methods.py","file_url":"https://github.com/zhangchbin/OnlineLabelSmoothing/blob/HEAD/cifar/scripts/train_cifar_all_methods.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6b88a61420e304e7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}