{"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-and-utilizing-deep-neural","title":"Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels","arxiv_id":"1905.05040","date":"2019-05-13","proceeding":null,"authors":["Pengfei Chen","Benben Liao","Guangyong Chen","Shengyu Zhang"],"abstract":"Noisy labels are ubiquitous in real-world datasets, which poses a challenge for robustly training deep neural networks (DNNs) as DNNs usually have the high capacity to memorize the noisy labels. In this paper, we find that the test accuracy can be quantitatively characterized in terms of the noise ratio in datasets. In particular, the test accuracy is a quadratic function of the noise ratio in the case of symmetric noise, which explains the experimental findings previously published. Based on our analysis, we apply cross-validation to randomly split noisy datasets, which identifies most samples that have correct labels. Then we adopt the Co-teaching strategy which takes full advantage of the identified samples to train DNNs robustly against noisy labels. Compared with extensive state-of-the-art methods, our strategy consistently improves the generalization performance of DNNs under both synthetic and real-world training noise.","url_abs":"https://arxiv.org/abs/1905.05040v1","url_pdf":"https://arxiv.org/pdf/1905.05040v1.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-and-utilizing-deep-neural","repo_url":"https://github.com/chenpf1025/noisy_label_understanding_utilizing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"understanding-and-utilizing-deep-neural","repo_url":"https://github.com/machine-learning-class-project/machine-learning-class-project.github.io","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"understanding-and-utilizing-deep-neural","repo_url":"https://github.com/noise-learning/selfmix","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-mini-webvision-1-0","task":"Image Classification","dataset":"mini WebVision 1.0","model":"Iterative-CV (Inception-ResNet-v2)","rank_in_archive_order":39,"of":47,"metrics":{"ImageNet Top-1 Accuracy":"61.6","ImageNet Top-5 Accuracy":"85.0","Top-1 Accuracy":"65.2","Top-5 Accuracy":"85.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1905.05040","atlas_url":"https://app.syntology.ai/?focus=1905.05040","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.05040"}},"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/machine-learning-class-project/machine-learning-class-project.github.io","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/noise-learning/selfmix","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chenpf1025/noisy_label_understanding_utilizing","reach":null}],"summary":{"ran_honours":3},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":"227a543993946c75","entry":"INCV_lr_schedule","repo":"chenpf1025/noisy_label_understanding_utilizing","repo_kind":"official","path":"INCV.py","file_url":"https://github.com/chenpf1025/noisy_label_understanding_utilizing/blob/HEAD/INCV.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"227a543993946c75"}},{"code_sha256_prefix":"ec43e02678d44f61","entry":"INCV_lr_schedule","repo":"chenpf1025/noisy_label_understanding_utilizing","repo_kind":"official","path":"INCV_main.py","file_url":"https://github.com/chenpf1025/noisy_label_understanding_utilizing/blob/HEAD/INCV_main.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ec43e02678d44f61"}},{"code_sha256_prefix":"fde7eb75fcfa9d2b","entry":"lr_schedule","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"fde7eb75fcfa9d2b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}