{"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/proselflc-progressive-self-label-correction","title":"ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks","arxiv_id":"2005.03788","date":"2020-05-07","proceeding":"CVPR 2021 1","authors":["Xinshao Wang","Yang Hua","Elyor Kodirov","David A. Clifton","Neil M. Robertson"],"abstract":"To train robust deep neural networks (DNNs), we systematically study several target modification approaches, which include output regularisation, self and non-self label correction (LC). Two key issues are discovered: (1) Self LC is the most appealing as it exploits its own knowledge and requires no extra models. However, how to automatically decide the trust degree of a learner as training goes is not well answered in the literature? (2) Some methods penalise while the others reward low-entropy predictions, prompting us to ask which one is better? To resolve the first issue, taking two well-accepted propositions--deep neural networks learn meaningful patterns before fitting noise [3] and minimum entropy regularisation principle [10]--we propose a novel end-to-end method named ProSelfLC, which is designed according to learning time and entropy. Specifically, given a data point, we progressively increase trust in its predicted label distribution versus its annotated one if a model has been trained for enough time and the prediction is of low entropy (high confidence). For the second issue, according to ProSelfLC, we empirically prove that it is better to redefine a meaningful low-entropy status and optimise the learner toward it. This serves as a defence of entropy minimisation. We demonstrate the effectiveness of ProSelfLC through extensive experiments in both clean and noisy settings. The source code is available at https://github.com/XinshaoAmosWang/ProSelfLC-CVPR2021. Keywords: entropy minimisation, maximum entropy, confidence penalty, self knowledge distillation, label correction, label noise, semi-supervised learning, output regularisation","url_abs":"https://arxiv.org/abs/2005.03788v6","url_pdf":"https://arxiv.org/pdf/2005.03788v6.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":"proselflc-progressive-self-label-correction","repo_url":"https://github.com/XinshaoAmosWang/ProSelfLC-CVPR2021","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"proselflc-progressive-self-label-correction","repo_url":"https://github.com/XinshaoAmosWang/ProSelfLC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"proselflc-progressive-self-label-correction","repo_url":"https://github.com/XinshaoAmosWang/ProSelfLC-CVPR21","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"proselflc-progressive-self-label-correction","repo_url":"https://github.com/kiyoon/pyvideoai","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"proselflc-progressive-self-label-correction","repo_url":"https://github.com/xinshaoamoswang/proselflc-at","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"self-knowledge-distillation","task_name":"Self-Knowledge Distillation"}],"methods":[{"method_slug":"label-smoothing","method_name":"Label Smoothing"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2005.03788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.03788"}},"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/xinshaoamoswang/proselflc-at","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/XinshaoAmosWang/ProSelfLC-CVPR21","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/XinshaoAmosWang/ProSelfLC","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/XinshaoAmosWang/ProSelfLC-CVPR2021","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kiyoon/pyvideoai","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":10},"by_repo_kind":{"listed":{"samples":11,"ran":1,"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":"2ce6782a49b98214","entry":"temporal_sampling","repo":"kiyoon/pyvideoai","repo_kind":"listed","path":"pyvideoai/dataloaders/decoder.py","file_url":"https://github.com/kiyoon/pyvideoai/blob/HEAD/pyvideoai/dataloaders/decoder.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2ce6782a49b98214"}},{"code_sha256_prefix":"4ccacd932d6aa3b7","entry":"count_class_frequency","repo":"kiyoon/pyvideoai","repo_kind":"listed","path":"pyvideoai/dataloaders/frames_sparsesample_dataset.py","file_url":"https://github.com/kiyoon/pyvideoai/blob/HEAD/pyvideoai/dataloaders/frames_sparsesample_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":"4ccacd932d6aa3b7"}},{"code_sha256_prefix":"532347378db99392","entry":"get_lr","repo":"kiyoon/pyvideoai","repo_kind":"listed","path":"pyvideoai/train_and_eval.py","file_url":"https://github.com/kiyoon/pyvideoai/blob/HEAD/pyvideoai/train_and_eval.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":"532347378db99392"}},{"code_sha256_prefix":"c366aa3be5213eaa","entry":"get_scheduler_type","repo":"kiyoon/pyvideoai","repo_kind":"listed","path":"pyvideoai/train_and_eval.py","file_url":"https://github.com/kiyoon/pyvideoai/blob/HEAD/pyvideoai/train_and_eval.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":"c366aa3be5213eaa"}},{"code_sha256_prefix":"c1a3191abe820a2c","entry":"get_start_end_idx","repo":"kiyoon/pyvideoai","repo_kind":"listed","path":"pyvideoai/dataloaders/decoder.py","file_url":"https://github.com/kiyoon/pyvideoai/blob/HEAD/pyvideoai/dataloaders/decoder.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":"c1a3191abe820a2c"}},{"code_sha256_prefix":"b28b46ef7776c434","entry":"pyav_decode_stream","repo":"kiyoon/pyvideoai","repo_kind":"listed","path":"pyvideoai/dataloaders/decoder.py","file_url":"https://github.com/kiyoon/pyvideoai/blob/HEAD/pyvideoai/dataloaders/decoder.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":"b28b46ef7776c434"}},{"code_sha256_prefix":"b06b3b57c757198b","entry":"register_vcs_handler","repo":"kiyoon/pyvideoai","repo_kind":"listed","path":"pyvideoai/_version.py","file_url":"https://github.com/kiyoon/pyvideoai/blob/HEAD/pyvideoai/_version.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":"b06b3b57c757198b"}},{"code_sha256_prefix":"c568a8377abe39e7","entry":"run_command","repo":"kiyoon/pyvideoai","repo_kind":"listed","path":"pyvideoai/_version.py","file_url":"https://github.com/kiyoon/pyvideoai/blob/HEAD/pyvideoai/_version.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":"c568a8377abe39e7"}},{"code_sha256_prefix":"db3b71c5b527f005","entry":"train_iter","repo":"kiyoon/pyvideoai","repo_kind":"listed","path":"pyvideoai/train_and_eval.py","file_url":"https://github.com/kiyoon/pyvideoai/blob/HEAD/pyvideoai/train_and_eval.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":"db3b71c5b527f005"}},{"code_sha256_prefix":"4adeea8f6880129b","entry":"turn_absolute","repo":"kiyoon/pyvideoai","repo_kind":"listed","path":"pyvideoai/config.py","file_url":"https://github.com/kiyoon/pyvideoai/blob/HEAD/pyvideoai/config.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":"4adeea8f6880129b"}},{"code_sha256_prefix":"b9a1535d27f2a9fb","entry":"versions_from_parentdir","repo":"kiyoon/pyvideoai","repo_kind":"listed","path":"pyvideoai/_version.py","file_url":"https://github.com/kiyoon/pyvideoai/blob/HEAD/pyvideoai/_version.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":"b9a1535d27f2a9fb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}