{"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/winning-ticket-in-noisy-image-classification","title":"FINE Samples for Learning with Noisy Labels","arxiv_id":"2102.11628","date":"2021-02-23","proceeding":"NeurIPS 2021 12","authors":["Taehyeon Kim","Jongwoo Ko","Sangwook Cho","Jinhwan Choi","Se-Young Yun"],"abstract":"Modern deep neural networks (DNNs) become frail when the datasets contain noisy (incorrect) class labels. Robust techniques in the presence of noisy labels can be categorized into two folds: developing noise-robust functions or using noise-cleansing methods by detecting the noisy data. Recently, noise-cleansing methods have been considered as the most competitive noisy-label learning algorithms. Despite their success, their noisy label detectors are often based on heuristics more than a theory, requiring a robust classifier to predict the noisy data with loss values. In this paper, we propose a novel detector for filtering label noise. Unlike most existing methods, we focus on each data's latent representation dynamics and measure the alignment between the latent distribution and each representation using the eigendecomposition of the data gram matrix. Our framework, coined as filtering noisy instances via their eigenvectors (FINE), provides a robust detector with derivative-free simple methods having theoretical guarantees. Under our framework, we propose three applications of the FINE: sample-selection approach, semi-supervised learning approach, and collaboration with noise-robust loss functions. Experimental results show that the proposed methods consistently outperform corresponding baselines for all three applications on various benchmark datasets.","url_abs":"https://arxiv.org/abs/2102.11628v3","url_pdf":"https://arxiv.org/pdf/2102.11628v3.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":"winning-ticket-in-noisy-image-classification","repo_url":"https://github.com/Kthyeon/FINE_official","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"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":"FINE + DivideMix","rank_in_archive_order":20,"of":51,"metrics":{"Accuracy":"74.37%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-webvision","task":"Image Classification","dataset":"WebVision","model":"FINE + DivideMix","rank_in_archive_order":2,"of":2,"metrics":{"Top 1 Accuracy":"77.28","Top 5 Accuracy":"91.44"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2102.11628","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11628"}},"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/Kthyeon/FINE_official","reach":null}],"summary":{"ran_fixture":4,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":7,"samples":[{"code_sha256_prefix":"742538aaa5b2f6da","entry":"cleansing","repo":"Kthyeon/FINE_official","repo_kind":"official","path":"dynamic_selection/selection/svd_classifier.py","file_url":"https://github.com/Kthyeon/FINE_official/blob/HEAD/dynamic_selection/selection/svd_classifier.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"742538aaa5b2f6da"}},{"code_sha256_prefix":"b4a9279205e76b98","entry":"fine","repo":"Kthyeon/FINE_official","repo_kind":"official","path":"dynamic_selection/selection/svd_classifier.py","file_url":"https://github.com/Kthyeon/FINE_official/blob/HEAD/dynamic_selection/selection/svd_classifier.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b4a9279205e76b98"}},{"code_sha256_prefix":"1c1cb9610be1000c","entry":"get_mean_vector","repo":"Kthyeon/FINE_official","repo_kind":"official","path":"dynamic_selection/selection/svd_classifier.py","file_url":"https://github.com/Kthyeon/FINE_official/blob/HEAD/dynamic_selection/selection/svd_classifier.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1c1cb9610be1000c"}},{"code_sha256_prefix":"1b10ac39415f471f","entry":"get_score","repo":"Kthyeon/FINE_official","repo_kind":"official","path":"dynamic_selection/selection/svd_classifier.py","file_url":"https://github.com/Kthyeon/FINE_official/blob/HEAD/dynamic_selection/selection/svd_classifier.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1b10ac39415f471f"}},{"code_sha256_prefix":"7566d840c21db4dc","entry":"get_singular_vector","repo":"Kthyeon/FINE_official","repo_kind":"official","path":"dynamic_selection/selection/svd_classifier.py","file_url":"https://github.com/Kthyeon/FINE_official/blob/HEAD/dynamic_selection/selection/svd_classifier.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7566d840c21db4dc"}},{"code_sha256_prefix":"8a2d14d95795c655","entry":"eval_train","repo":"kthyeon/fine_official","repo_kind":"official","path":"dividemix/Train_cifar.py","file_url":"https://github.com/kthyeon/fine_official/blob/HEAD/dividemix/Train_cifar.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8a2d14d95795c655"}},{"code_sha256_prefix":"767f49a34c3cb79a","entry":"linear_rampup","repo":"kthyeon/fine_official","repo_kind":"official","path":"dividemix/Train_cifar.py","file_url":"https://github.com/kthyeon/fine_official/blob/HEAD/dividemix/Train_cifar.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"767f49a34c3cb79a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}