{"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/dividemix-learning-with-noisy-labels-as-semi-1","title":"DivideMix: Learning with Noisy Labels as Semi-supervised Learning","arxiv_id":"2002.07394","date":"2020-02-18","proceeding":"ICLR 2020 1","authors":["Junnan Li","Richard Socher","Steven C. H. Hoi"],"abstract":"Deep neural networks are known to be annotation-hungry. Numerous efforts have been devoted to reducing the annotation cost when learning with deep networks. Two prominent directions include learning with noisy labels and semi-supervised learning by exploiting unlabeled data. In this work, we propose DivideMix, a novel framework for learning with noisy labels by leveraging semi-supervised learning techniques. In particular, DivideMix models the per-sample loss distribution with a mixture model to dynamically divide the training data into a labeled set with clean samples and an unlabeled set with noisy samples, and trains the model on both the labeled and unlabeled data in a semi-supervised manner. To avoid confirmation bias, we simultaneously train two diverged networks where each network uses the dataset division from the other network. During the semi-supervised training phase, we improve the MixMatch strategy by performing label co-refinement and label co-guessing on labeled and unlabeled samples, respectively. Experiments on multiple benchmark datasets demonstrate substantial improvements over state-of-the-art methods. Code is available at https://github.com/LiJunnan1992/DivideMix .","url_abs":"https://arxiv.org/abs/2002.07394v1","url_pdf":"https://arxiv.org/pdf/2002.07394v1.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":"dividemix-learning-with-noisy-labels-as-semi-1","repo_url":"https://github.com/LiJunnan1992/DivideMix","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"dividemix-learning-with-noisy-labels-as-semi-1","repo_url":"https://github.com/jyansir/text2tree","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"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-clothing1m","task":"Image Classification","dataset":"Clothing1M","model":"DivideMix","rank_in_archive_order":15,"of":51,"metrics":{"Accuracy":"74.76%"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-mini-webvision-1-0","task":"Image Classification","dataset":"mini WebVision 1.0","model":"DivideMix (Inception-ResNet-v2)","rank_in_archive_order":31,"of":47,"metrics":{"ImageNet Top-1 Accuracy":"75.20","ImageNet Top-5 Accuracy":"91.64","Top-1 Accuracy":"77.32","Top-5 Accuracy":"91.64"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mini-webvision-1-0","task":"Image Classification","dataset":"mini WebVision 1.0","model":"DivideMix (ResNet-50)","rank_in_archive_order":33,"of":47,"metrics":{"ImageNet Top-1 Accuracy":"74.42 ±0.29","ImageNet Top-5 Accuracy":"91.21 ±0.12","Top-1 Accuracy":"76.32 ±0.36","Top-5 Accuracy":"90.65 ±0.16"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mini-webvision-1-0","task":"Image Classification","dataset":"mini WebVision 1.0","model":"DivideMix (ResNet-18)","rank_in_archive_order":34,"of":47,"metrics":{"Top-1 Accuracy":"76.08"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-100n","task":"Learning with noisy labels","dataset":"CIFAR-100N","model":"Divide-Mix","rank_in_archive_order":4,"of":24,"metrics":{"Accuracy (mean)":"71.13"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n","task":"Learning with noisy labels","dataset":"CIFAR-10N-Aggregate","model":"Divide-Mix","rank_in_archive_order":7,"of":26,"metrics":{"Accuracy (mean)":"95.01"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n-1","task":"Learning with noisy labels","dataset":"CIFAR-10N-Random1","model":"Divide-Mix","rank_in_archive_order":14,"of":24,"metrics":{"Accuracy (mean)":"90.18"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n-2","task":"Learning with noisy labels","dataset":"CIFAR-10N-Random2","model":"Divide-Mix","rank_in_archive_order":8,"of":23,"metrics":{"Accuracy (mean)":"90.90"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n-3","task":"Learning with noisy labels","dataset":"CIFAR-10N-Random3","model":"Divide-Mix","rank_in_archive_order":12,"of":23,"metrics":{"Accuracy (mean)":"89.97"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n-worst","task":"Learning with noisy labels","dataset":"CIFAR-10N-Worst","model":"Divide-Mix","rank_in_archive_order":6,"of":25,"metrics":{"Accuracy (mean)":"92.56"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2002.07394","atlas_url":"https://app.syntology.ai/?focus=2002.07394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.07394"}},"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/LiJunnan1992/DivideMix","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jyansir/text2tree","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":2},"by_repo_kind":{},"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":2,"samples":[{"code_sha256_prefix":"8a2d14d95795c655","entry":"eval_train","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"8a2d14d95795c655"}},{"code_sha256_prefix":"767f49a34c3cb79a","entry":"linear_rampup","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"767f49a34c3cb79a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}