{"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/identifying-hard-noise-in-long-tailed-sample","title":"Identifying Hard Noise in Long-Tailed Sample Distribution","arxiv_id":"2207.13378","date":"2022-07-27","proceeding":null,"authors":["Xuanyu Yi","Kaihua Tang","Xian-Sheng Hua","Joo-Hwee Lim","Hanwang Zhang"],"abstract":"Conventional de-noising methods rely on the assumption that all samples are independent and identically distributed, so the resultant classifier, though disturbed by noise, can still easily identify the noises as the outliers of training distribution. However, the assumption is unrealistic in large-scale data that is inevitably long-tailed. Such imbalanced training data makes a classifier less discriminative for the tail classes, whose previously \"easy\" noises are now turned into \"hard\" ones -- they are almost as outliers as the clean tail samples. We introduce this new challenge as Noisy Long-Tailed Classification (NLT). Not surprisingly, we find that most de-noising methods fail to identify the hard noises, resulting in significant performance drop on the three proposed NLT benchmarks: ImageNet-NLT, Animal10-NLT, and Food101-NLT. To this end, we design an iterative noisy learning framework called Hard-to-Easy (H2E). Our bootstrapping philosophy is to first learn a classifier as noise identifier invariant to the class and context distributional changes, reducing \"hard\" noises to \"easy\" ones, whose removal further improves the invariance. Experimental results show that our H2E outperforms state-of-the-art de-noising methods and their ablations on long-tailed settings while maintaining a stable performance on the conventional balanced settings. Datasets and codes are available at https://github.com/yxymessi/H2E-Framework","url_abs":"https://arxiv.org/abs/2207.13378v2","url_pdf":"https://arxiv.org/pdf/2207.13378v2.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":"identifying-hard-noise-in-long-tailed-sample","repo_url":"https://github.com/yxymessi/h2e-framework","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"philosophy","task_name":"Philosophy"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.13378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.13378"}},"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/yxymessi/h2e-framework","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/yxymessi/H2E-Framework","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran_fixture":1,"unverified":9},"by_repo_kind":{"official":{"samples":11,"ran":2,"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":"7937f88152d63f61","entry":"call_bn","repo":"yxymessi/H2E-Framework","repo_kind":"official","path":"eccv_github/noise_longtail/code/model.py","file_url":"https://github.com/yxymessi/H2E-Framework/blob/HEAD/eccv_github/noise_longtail/code/model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7937f88152d63f61"}},{"code_sha256_prefix":"fd81207449c239dd","entry":"mixup_data","repo":"yxymessi/H2E-Framework","repo_kind":"official","path":"eccv_github/noise_longtail/code/utils.py","file_url":"https://github.com/yxymessi/H2E-Framework/blob/HEAD/eccv_github/noise_longtail/code/utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd81207449c239dd"}},{"code_sha256_prefix":"2d468638b40f3381","entry":"compute_adjustment","repo":"yxymessi/H2E-Framework","repo_kind":"official","path":"eccv_github/noise_longtail/code/stage1.py","file_url":"https://github.com/yxymessi/H2E-Framework/blob/HEAD/eccv_github/noise_longtail/code/stage1.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":"2d468638b40f3381"}},{"code_sha256_prefix":"6c1b73e88ea70693","entry":"count_dataset","repo":"yxymessi/H2E-Framework","repo_kind":"official","path":"eccv_github/noise_longtail/code/loss.py","file_url":"https://github.com/yxymessi/H2E-Framework/blob/HEAD/eccv_github/noise_longtail/code/loss.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":"6c1b73e88ea70693"}},{"code_sha256_prefix":"e6571d10bfbf14f3","entry":"create_classifer","repo":"yxymessi/H2E-Framework","repo_kind":"official","path":"eccv_github/noise_longtail/code/model.py","file_url":"https://github.com/yxymessi/H2E-Framework/blob/HEAD/eccv_github/noise_longtail/code/model.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":"e6571d10bfbf14f3"}},{"code_sha256_prefix":"5cbc579cb1e2d98a","entry":"create_model","repo":"yxymessi/H2E-Framework","repo_kind":"official","path":"eccv_github/noise_longtail/code/model.py","file_url":"https://github.com/yxymessi/H2E-Framework/blob/HEAD/eccv_github/noise_longtail/code/model.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":"5cbc579cb1e2d98a"}},{"code_sha256_prefix":"098713e67b736d08","entry":"loss_coteaching","repo":"yxymessi/H2E-Framework","repo_kind":"official","path":"eccv_github/noise_longtail/code/loss.py","file_url":"https://github.com/yxymessi/H2E-Framework/blob/HEAD/eccv_github/noise_longtail/code/loss.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":"098713e67b736d08"}},{"code_sha256_prefix":"79edc1957c1e3747","entry":"mixup_criterion","repo":"yxymessi/H2E-Framework","repo_kind":"official","path":"eccv_github/noise_longtail/code/utils.py","file_url":"https://github.com/yxymessi/H2E-Framework/blob/HEAD/eccv_github/noise_longtail/code/utils.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":"79edc1957c1e3747"}},{"code_sha256_prefix":"aad6a1787762c8ee","entry":"mixup_data_weight","repo":"yxymessi/H2E-Framework","repo_kind":"official","path":"eccv_github/noise_longtail/code/utils.py","file_url":"https://github.com/yxymessi/H2E-Framework/blob/HEAD/eccv_github/noise_longtail/code/utils.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":"aad6a1787762c8ee"}},{"code_sha256_prefix":"5007bbe5663c0042","entry":"read_data","repo":"yxymessi/H2E-Framework","repo_kind":"official","path":"eccv_github/noise_longtail/construct_data/get_dataset.py","file_url":"https://github.com/yxymessi/H2E-Framework/blob/HEAD/eccv_github/noise_longtail/construct_data/get_dataset.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":"5007bbe5663c0042"}},{"code_sha256_prefix":"07cca9631fe4f26a","entry":"source_import","repo":"yxymessi/H2E-Framework","repo_kind":"official","path":"eccv_github/noise_longtail/code/stage1.py","file_url":"https://github.com/yxymessi/H2E-Framework/blob/HEAD/eccv_github/noise_longtail/code/stage1.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":"07cca9631fe4f26a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}