{"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/learning-with-neighbor-consistency-for-noisy-1","title":"Learning with Neighbor Consistency for Noisy Labels","arxiv_id":"2202.02200","date":"2022-02-04","proceeding":"CVPR 2022 1","authors":["Ahmet Iscen","Jack Valmadre","Anurag Arnab","Cordelia Schmid"],"abstract":"Recent advances in deep learning have relied on large, labelled datasets to train high-capacity models. However, collecting large datasets in a time- and cost-efficient manner often results in label noise. We present a method for learning from noisy labels that leverages similarities between training examples in feature space, encouraging the prediction of each example to be similar to its nearest neighbours. Compared to training algorithms that use multiple models or distinct stages, our approach takes the form of a simple, additional regularization term. It can be interpreted as an inductive version of the classical, transductive label propagation algorithm. We thoroughly evaluate our method on datasets evaluating both synthetic (CIFAR-10, CIFAR-100) and realistic (mini-WebVision, WebVision, Clothing1M, mini-ImageNet-Red) noise, and achieve competitive or state-of-the-art accuracies across all of them.","url_abs":"https://arxiv.org/abs/2202.02200v2","url_pdf":"https://arxiv.org/pdf/2202.02200v2.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":"learning-with-neighbor-consistency-for-noisy-1","repo_url":"https://github.com/google-research/scenic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null}],"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-red-miniimagenet-20","task":"Image Classification","dataset":"Red MiniImageNet 20% label noise","model":"NCR (ResNet-18)","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"69.0"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-red-miniimagenet-40","task":"Image Classification","dataset":"Red MiniImageNet 40% label noise","model":"NCR (ResNet-18)","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"64.6"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-red-miniimagenet-80","task":"Image Classification","dataset":"Red MiniImageNet 80% label noise","model":"NCR (ResNet-18)","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"51.2"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-webvision-1000","task":"Image Classification","dataset":"WebVision-1000","model":"NCR+Mixup+DA (ResNet-50)","rank_in_archive_order":4,"of":16,"metrics":{"Top-1 Accuracy":"76.8"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-webvision-1000","task":"Image Classification","dataset":"WebVision-1000","model":"NCR (ResNet-50)","rank_in_archive_order":8,"of":16,"metrics":{"Top-1 Accuracy":"75.7%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mini-webvision-1-0","task":"Image Classification","dataset":"mini WebVision 1.0","model":"NCR+Mixup+DA (ResNet-50)","rank_in_archive_order":7,"of":47,"metrics":{"Top-1 Accuracy":"80.5"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mini-webvision-1-0","task":"Image Classification","dataset":"mini WebVision 1.0","model":"NCR+Mixup (ResNet-50)","rank_in_archive_order":16,"of":47,"metrics":{"Top-1 Accuracy":"79.4"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mini-webvision-1-0","task":"Image Classification","dataset":"mini WebVision 1.0","model":"NCR (ResNet-50)","rank_in_archive_order":32,"of":47,"metrics":{"Top-1 Accuracy":"77.1"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-red","task":"Learning with noisy labels","dataset":"Red MiniImageNet 20% label noise","model":"NCR (ResNet-18)","rank_in_archive_order":1,"of":4,"metrics":{"Test Accuracy":"69.0"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-red-1","task":"Learning with noisy labels","dataset":"Red MiniImageNet 40% label noise","model":"NCR (ResNet-18)","rank_in_archive_order":1,"of":4,"metrics":{"Test Accuracy":"64.6"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-red-3","task":"Learning with noisy labels","dataset":"Red MiniImageNet 80% label noise","model":"NCR (ResNet-18)","rank_in_archive_order":1,"of":4,"metrics":{"Test Accuracy":"51.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2202.02200","atlas_url":"https://app.syntology.ai/?focus=2202.02200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.02200"}},"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/google-research/scenic","reach":null}],"summary":{"ran_fixture":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"06fab7164d5f04d0","entry":"get_knn","repo":"google-research/scenic","repo_kind":"official","path":"scenic/projects/ncr/loss.py","file_url":"https://github.com/google-research/scenic/blob/HEAD/scenic/projects/ncr/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"06fab7164d5f04d0"}},{"code_sha256_prefix":"d473d69bb4e6da8e","entry":"l2_normalize","repo":"google-research/scenic","repo_kind":"official","path":"scenic/projects/ncr/loss.py","file_url":"https://github.com/google-research/scenic/blob/HEAD/scenic/projects/ncr/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d473d69bb4e6da8e"}},{"code_sha256_prefix":"f1339fb095cb07a5","entry":"ncr_loss","repo":"google-research/scenic","repo_kind":"official","path":"scenic/projects/ncr/loss.py","file_url":"https://github.com/google-research/scenic/blob/HEAD/scenic/projects/ncr/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f1339fb095cb07a5"}},{"code_sha256_prefix":"78743aa08f1f1c21","entry":"pairwise_kl_loss","repo":"google-research/scenic","repo_kind":"official","path":"scenic/projects/ncr/loss.py","file_url":"https://github.com/google-research/scenic/blob/HEAD/scenic/projects/ncr/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"78743aa08f1f1c21"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}