{"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/iterative-learning-with-open-set-noisy-labels","title":"Iterative Learning with Open-set Noisy Labels","arxiv_id":"1804.00092","date":"2018-03-31","proceeding":"CVPR 2018 6","authors":["Yisen Wang","Weiyang Liu","Xingjun Ma","James Bailey","Hongyuan Zha","Le Song","Shu-Tao Xia"],"abstract":"Large-scale datasets possessing clean label annotations are crucial for\ntraining Convolutional Neural Networks (CNNs). However, labeling large-scale\ndata can be very costly and error-prone, and even high-quality datasets are\nlikely to contain noisy (incorrect) labels. Existing works usually employ a\nclosed-set assumption, whereby the samples associated with noisy labels possess\na true class contained within the set of known classes in the training data.\nHowever, such an assumption is too restrictive for many applications, since\nsamples associated with noisy labels might in fact possess a true class that is\nnot present in the training data. We refer to this more complex scenario as the\n\\textbf{open-set noisy label} problem and show that it is nontrivial in order\nto make accurate predictions. To address this problem, we propose a novel\niterative learning framework for training CNNs on datasets with open-set noisy\nlabels. Our approach detects noisy labels and learns deep discriminative\nfeatures in an iterative fashion. To benefit from the noisy label detection, we\ndesign a Siamese network to encourage clean labels and noisy labels to be\ndissimilar. A reweighting module is also applied to simultaneously emphasize\nthe learning from clean labels and reduce the effect caused by noisy labels.\nExperiments on CIFAR-10, ImageNet and real-world noisy (web-search) datasets\ndemonstrate that our proposed model can robustly train CNNs in the presence of\na high proportion of open-set as well as closed-set noisy labels.","url_abs":"http://arxiv.org/abs/1804.00092v1","url_pdf":"http://arxiv.org/pdf/1804.00092v1.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":"iterative-learning-with-open-set-noisy-labels","repo_url":"https://github.com/YisenWang/ONL","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[{"method_slug":"siamese-network","method_name":"Siamese Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.00092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.00092"}},"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/YisenWang/ONL","reach":null}],"summary":{"ran_fixture":1},"by_repo_kind":{"official":{"samples":1,"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":"cc8acac4816ccb95","entry":"eucl_dist_output_shape","repo":"YisenWang/ONL","repo_kind":"official","path":"train_model_openset.py","file_url":"https://github.com/YisenWang/ONL/blob/HEAD/train_model_openset.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cc8acac4816ccb95"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}