{"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/centrality-and-consistency-two-stage-clean","title":"Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels","arxiv_id":"2207.14476","date":"2022-07-29","proceeding":null,"authors":["Ganlong Zhao","Guanbin Li","Yipeng Qin","Feng Liu","Yizhou Yu"],"abstract":"Deep models trained with noisy labels are prone to over-fitting and struggle in generalization. Most existing solutions are based on an ideal assumption that the label noise is class-conditional, i.e., instances of the same class share the same noise model, and are independent of features. While in practice, the real-world noise patterns are usually more fine-grained as instance-dependent ones, which poses a big challenge, especially in the presence of inter-class imbalance. In this paper, we propose a two-stage clean samples identification method to address the aforementioned challenge. First, we employ a class-level feature clustering procedure for the early identification of clean samples that are near the class-wise prediction centers. Notably, we address the class imbalance problem by aggregating rare classes according to their prediction entropy. Second, for the remaining clean samples that are close to the ground truth class boundary (usually mixed with the samples with instance-dependent noises), we propose a novel consistency-based classification method that identifies them using the consistency of two classifier heads: the higher the consistency, the larger the probability that a sample is clean. Extensive experiments on several challenging benchmarks demonstrate the superior performance of our method against the state-of-the-art.","url_abs":"https://arxiv.org/abs/2207.14476v1","url_pdf":"https://arxiv.org/pdf/2207.14476v1.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":"centrality-and-consistency-two-stage-clean","repo_url":"https://github.com/uitrbn/tscsi_idn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-clothing1m","task":"Image Classification","dataset":"Clothing1M","model":"CC","rank_in_archive_order":4,"of":51,"metrics":{"Accuracy":"75.4%"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-mini-webvision-1-0","task":"Image Classification","dataset":"mini WebVision 1.0","model":"CC","rank_in_archive_order":17,"of":47,"metrics":{"ImageNet Top-1 Accuracy":"76.08","ImageNet Top-5 Accuracy":"93.86","Top-1 Accuracy":"79.36","Top-5 Accuracy":"93.64"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2207.14476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.14476"}},"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/uitrbn/tscsi_idn","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/uitrbn/TSCSI_IDN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"ran":1,"unverified":5},"by_repo_kind":{"official":{"samples":9,"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":"7b20f1288903c47c","entry":"ResNet18","repo":"uitrbn/TSCSI_IDN","repo_kind":"official","path":"PreResNet.py","file_url":"https://github.com/uitrbn/TSCSI_IDN/blob/HEAD/PreResNet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b20f1288903c47c"}},{"code_sha256_prefix":"eee26fa0aef03470","entry":"ResNet34","repo":"uitrbn/TSCSI_IDN","repo_kind":"official","path":"PreResNet.py","file_url":"https://github.com/uitrbn/TSCSI_IDN/blob/HEAD/PreResNet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eee26fa0aef03470"}},{"code_sha256_prefix":"583f9780bdd00a45","entry":"conv3x3","repo":"uitrbn/TSCSI_IDN","repo_kind":"official","path":"PreResNet.py","file_url":"https://github.com/uitrbn/TSCSI_IDN/blob/HEAD/PreResNet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"583f9780bdd00a45"}},{"code_sha256_prefix":"ef49e82a7403eee1","entry":"unpickle","repo":"uitrbn/TSCSI_IDN","repo_kind":"official","path":"dataloader_cifar_idn_part.py","file_url":"https://github.com/uitrbn/TSCSI_IDN/blob/HEAD/dataloader_cifar_idn_part.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ef49e82a7403eee1"}},{"code_sha256_prefix":"8563a67136078a4c","entry":"create_model_discrepancy","repo":"uitrbn/TSCSI_IDN","repo_kind":"official","path":"models/networks.py","file_url":"https://github.com/uitrbn/TSCSI_IDN/blob/HEAD/models/networks.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8563a67136078a4c"}},{"code_sha256_prefix":"d609a2f53238c07d","entry":"eval_train_clustering","repo":"uitrbn/TSCSI_IDN","repo_kind":"official","path":"Train_clothing1m.py","file_url":"https://github.com/uitrbn/TSCSI_IDN/blob/HEAD/Train_clothing1m.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d609a2f53238c07d"}},{"code_sha256_prefix":"42389b7e441102f3","entry":"get_discrepancy","repo":"uitrbn/TSCSI_IDN","repo_kind":"official","path":"Train_cifar.py","file_url":"https://github.com/uitrbn/TSCSI_IDN/blob/HEAD/Train_cifar.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"42389b7e441102f3"}},{"code_sha256_prefix":"d4f8d5fd490a7681","entry":"get_discrepancy","repo":"uitrbn/TSCSI_IDN","repo_kind":"official","path":"Train_clothing1m.py","file_url":"https://github.com/uitrbn/TSCSI_IDN/blob/HEAD/Train_clothing1m.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d4f8d5fd490a7681"}},{"code_sha256_prefix":"d988d4a899c17d25","entry":"test_epoch","repo":"uitrbn/TSCSI_IDN","repo_kind":"official","path":"Train_cifar.py","file_url":"https://github.com/uitrbn/TSCSI_IDN/blob/HEAD/Train_cifar.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d988d4a899c17d25"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}