{"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/in-defense-of-pseudo-labeling-an-uncertainty-1","title":"In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning","arxiv_id":"2101.06329","date":"2021-01-15","proceeding":"ICLR 2021 1","authors":["Mamshad Nayeem Rizve","Kevin Duarte","Yogesh S Rawat","Mubarak Shah"],"abstract":"The recent research in semi-supervised learning (SSL) is mostly dominated by consistency regularization based methods which achieve strong performance. However, they heavily rely on domain-specific data augmentations, which are not easy to generate for all data modalities. Pseudo-labeling (PL) is a general SSL approach that does not have this constraint but performs relatively poorly in its original formulation. We argue that PL underperforms due to the erroneous high confidence predictions from poorly calibrated models; these predictions generate many incorrect pseudo-labels, leading to noisy training. We propose an uncertainty-aware pseudo-label selection (UPS) framework which improves pseudo labeling accuracy by drastically reducing the amount of noise encountered in the training process. Furthermore, UPS generalizes the pseudo-labeling process, allowing for the creation of negative pseudo-labels; these negative pseudo-labels can be used for multi-label classification as well as negative learning to improve the single-label classification. We achieve strong performance when compared to recent SSL methods on the CIFAR-10 and CIFAR-100 datasets. Also, we demonstrate the versatility of our method on the video dataset UCF-101 and the multi-label dataset Pascal VOC.","url_abs":"https://arxiv.org/abs/2101.06329v3","url_pdf":"https://arxiv.org/pdf/2101.06329v3.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":"in-defense-of-pseudo-labeling-an-uncertainty-1","repo_url":"https://github.com/nayeemrizve/ups","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"in-defense-of-pseudo-labeling-an-uncertainty-1","repo_url":"https://github.com/matinmoezzi/ups_conformal_classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multi-label-classification-2","task_name":"MUlTI-LABEL-ClASSIFICATION"},{"task_slug":"multi-label-classification","task_name":"Multi-Label Classification"},{"task_slug":"pseudo-label","task_name":"Pseudo Label"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"},{"task_slug":"semi-supervised-video-classification","task_name":"Semi-Supervised Video Classification"},{"task_slug":"semi-supervised-medical-image-classification","task_name":"Semi-supervised Medical Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-11","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 1000 Labels","model":"UPS (CNN-13)","rank_in_archive_order":2,"of":9,"metrics":{"Accuracy":"91.82"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 4000 Labels","model":"UPS (Shake-Shake)","rank_in_archive_order":21,"of":49,"metrics":{"Percentage error":"4.86"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 4000 Labels","model":"UPS (CNN-13)","rank_in_archive_order":33,"of":49,"metrics":{"Percentage error":"6.39±0.02"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-20","task":"Semi-Supervised Image Classification","dataset":"CIFAR-100, 4000 Labels","model":"UPS (CNN-13)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"59.23"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-2","task":"Semi-Supervised Image Classification","dataset":"cifar-100, 10000 Labels","model":"UPS (CNN-13)","rank_in_archive_order":24,"of":29,"metrics":{"Percentage error":"32"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-medical-image-classification-1","task":"Semi-supervised Medical Image Classification","dataset":"Chest X-Ray14 2% labeled","model":"UPS","rank_in_archive_order":3,"of":4,"metrics":{"AUC":"65.51"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2101.06329","atlas_url":"https://app.syntology.ai/?focus=2101.06329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.06329"}},"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":"deterministic:regex_extraction","url":"https://github.com/nayeemrizve/ups","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/matinmoezzi/ups_conformal_classification","reach":null}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1},"listed":{"samples":3,"ran":0,"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":3,"samples":[{"code_sha256_prefix":"f525d64dc7aa3516","entry":"accuracy","repo":"matinmoezzi/ups_conformal_classification","repo_kind":"listed","path":"utils/pseudo_labeling_util.py","file_url":"https://github.com/matinmoezzi/ups_conformal_classification/blob/HEAD/utils/pseudo_labeling_util.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":"f525d64dc7aa3516"}},{"code_sha256_prefix":"b61c4c542a153e87","entry":"cnn13","repo":"nayeemrizve/ups","repo_kind":"official","path":"models/cnn13.py","file_url":"https://github.com/nayeemrizve/ups/blob/HEAD/models/cnn13.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b61c4c542a153e87"}},{"code_sha256_prefix":"586ccfec218401dd","entry":"enable_dropout","repo":"matinmoezzi/ups_conformal_classification","repo_kind":"listed","path":"utils/pseudo_labeling_util.py","file_url":"https://github.com/matinmoezzi/ups_conformal_classification/blob/HEAD/utils/pseudo_labeling_util.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":"586ccfec218401dd"}},{"code_sha256_prefix":"58c42391c2ccd1ae","entry":"pseudo_labeling","repo":"nayeemrizve/ups","repo_kind":"official","path":"utils/pseudo_labeling_util.py","file_url":"https://github.com/nayeemrizve/ups/blob/HEAD/utils/pseudo_labeling_util.py","link_basis":"first_harvest_node","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":"58c42391c2ccd1ae"}},{"code_sha256_prefix":"b0e6dd249d2917c0","entry":"pseudo_labeling","repo":"matinmoezzi/ups_conformal_classification","repo_kind":"listed","path":"utils/pseudo_labeling_util.py","file_url":"https://github.com/matinmoezzi/ups_conformal_classification/blob/HEAD/utils/pseudo_labeling_util.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":"b0e6dd249d2917c0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}