{"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/190600189","title":"Are Anchor Points Really Indispensable in Label-Noise Learning?","arxiv_id":"1906.00189","date":"2019-06-01","proceeding":"NeurIPS 2019 12","authors":["Xiaobo Xia","Tongliang Liu","Nannan Wang","Bo Han","Chen Gong","Gang Niu","Masashi Sugiyama"],"abstract":"In label-noise learning, \\textit{noise transition matrix}, denoting the probabilities that clean labels flip into noisy labels, plays a central role in building \\textit{statistically consistent classifiers}. Existing theories have shown that the transition matrix can be learned by exploiting \\textit{anchor points} (i.e., data points that belong to a specific class almost surely). However, when there are no anchor points, the transition matrix will be poorly learned, and those current consistent classifiers will significantly degenerate. In this paper, without employing anchor points, we propose a \\textit{transition-revision} ($T$-Revision) method to effectively learn transition matrices, leading to better classifiers. Specifically, to learn a transition matrix, we first initialize it by exploiting data points that are similar to anchor points, having high \\textit{noisy class posterior probabilities}. Then, we modify the initialized matrix by adding a \\textit{slack variable}, which can be learned and validated together with the classifier by using noisy data. Empirical results on benchmark-simulated and real-world label-noise datasets demonstrate that without using exact anchor points, the proposed method is superior to the state-of-the-art label-noise learning methods.","url_abs":"https://arxiv.org/abs/1906.00189v2","url_pdf":"https://arxiv.org/pdf/1906.00189v2.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":"190600189","repo_url":"https://github.com/xiaoboxia/T-Revision","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"learning-with-noisy-labels","task_name":"Learning with noisy labels"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-100n","task":"Learning with noisy labels","dataset":"CIFAR-100N","model":"T-Revision","rank_in_archive_order":24,"of":24,"metrics":{"Accuracy (mean)":"51.55"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n","task":"Learning with noisy labels","dataset":"CIFAR-10N-Aggregate","model":"T-Revision","rank_in_archive_order":22,"of":26,"metrics":{"Accuracy (mean)":"88.52"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n-1","task":"Learning with noisy labels","dataset":"CIFAR-10N-Random1","model":"T-Revision","rank_in_archive_order":20,"of":24,"metrics":{"Accuracy (mean)":"88.33"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n-2","task":"Learning with noisy labels","dataset":"CIFAR-10N-Random2","model":"T-Revision","rank_in_archive_order":19,"of":23,"metrics":{"Accuracy (mean)":"87.71"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n-3","task":"Learning with noisy labels","dataset":"CIFAR-10N-Random3","model":"T-Revision","rank_in_archive_order":19,"of":23,"metrics":{"Accuracy (mean)":"87.79"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-cifar-10n-worst","task":"Learning with noisy labels","dataset":"CIFAR-10N-Worst","model":"T-Revision","rank_in_archive_order":22,"of":25,"metrics":{"Accuracy (mean)":"80.48"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.00189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.00189"}},"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/xiaoboxia/T-Revision","reach":null}],"summary":{"ran_violates":1,"ran_draft_wrong":2},"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":"fac9904f665a5702","entry":"check_integrity","repo":"xiaoboxia/T-Revision","repo_kind":"official","path":"utils.py","file_url":"https://github.com/xiaoboxia/T-Revision/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fac9904f665a5702"}},{"code_sha256_prefix":"915e1c6c38494be9","entry":"list_dir","repo":"xiaoboxia/T-Revision","repo_kind":"official","path":"utils.py","file_url":"https://github.com/xiaoboxia/T-Revision/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"915e1c6c38494be9"}},{"code_sha256_prefix":"208e196e9582a9a6","entry":"list_files","repo":"xiaoboxia/T-Revision","repo_kind":"official","path":"utils.py","file_url":"https://github.com/xiaoboxia/T-Revision/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"208e196e9582a9a6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}