{"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/pseudo-labeling-and-confirmation-bias-in-deep","title":"Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning","arxiv_id":"1908.02983","date":"2019-08-08","proceeding":null,"authors":["Eric Arazo","Diego Ortego","Paul Albert","Noel E. O'Connor","Kevin McGuinness"],"abstract":"Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active research topic due to its key role on relaxing human supervision. In the context of image classification, recent advances to learn from unlabeled samples are mainly focused on consistency regularization methods that encourage invariant predictions for different perturbations of unlabeled samples. We, conversely, propose to learn from unlabeled data by generating soft pseudo-labels using the network predictions. We show that a naive pseudo-labeling overfits to incorrect pseudo-labels due to the so-called confirmation bias and demonstrate that mixup augmentation and setting a minimum number of labeled samples per mini-batch are effective regularization techniques for reducing it. The proposed approach achieves state-of-the-art results in CIFAR-10/100, SVHN, and Mini-ImageNet despite being much simpler than other methods. These results demonstrate that pseudo-labeling alone can outperform consistency regularization methods, while the opposite was supposed in previous work. Source code is available at https://git.io/fjQsC.","url_abs":"https://arxiv.org/abs/1908.02983v5","url_pdf":"https://arxiv.org/pdf/1908.02983v5.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":"pseudo-labeling-and-confirmation-bias-in-deep","repo_url":"https://github.com/5m0k3/gwd-efficientdet-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"pseudo-labeling-and-confirmation-bias-in-deep","repo_url":"https://github.com/5m0k3/gwd-yolov5-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"pseudo-labeling-and-confirmation-bias-in-deep","repo_url":"https://github.com/EricArazo/PseudoLabeling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"pseudo-labeling-and-confirmation-bias-in-deep","repo_url":"https://github.com/stanleyjzheng/PyData","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"mixup","method_name":"Mixup"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1908.02983","atlas_url":"https://app.syntology.ai/?focus=1908.02983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.02983"}},"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/EricArazo/PseudoLabeling","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/5m0k3/gwd-yolov5-pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stanleyjzheng/PyData","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/5m0k3/gwd-efficientdet-pytorch","reach":{"status":"ok"}}],"summary":{"ran":9,"ran_draft_wrong":2,"unverified":9},"by_repo_kind":{"listed":{"samples":20,"ran":11,"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":"cac73dbdc6c8edf8","entry":"PreactResNet18_WNdrop","repo":"EricArazo/PseudoLabeling","repo_kind":"listed","path":"utils_pseudoLab/PreResNet.py","file_url":"https://github.com/EricArazo/PseudoLabeling/blob/HEAD/utils_pseudoLab/PreResNet.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":"cac73dbdc6c8edf8"}},{"code_sha256_prefix":"19760465fa4284bf","entry":"WRN28_2_wn","repo":"EricArazo/PseudoLabeling","repo_kind":"listed","path":"utils_pseudoLab/wideArchitectures.py","file_url":"https://github.com/EricArazo/PseudoLabeling/blob/HEAD/utils_pseudoLab/wideArchitectures.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":"19760465fa4284bf"}},{"code_sha256_prefix":"158bf4c3a5f11f04","entry":"conv1x1","repo":"EricArazo/PseudoLabeling","repo_kind":"listed","path":"utils_pseudoLab/ssl_networks.py","file_url":"https://github.com/EricArazo/PseudoLabeling/blob/HEAD/utils_pseudoLab/ssl_networks.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":"158bf4c3a5f11f04"}},{"code_sha256_prefix":"00e569acd6b45ef0","entry":"conv3x3","repo":"EricArazo/PseudoLabeling","repo_kind":"listed","path":"utils_pseudoLab/wideArchitectures.py","file_url":"https://github.com/EricArazo/PseudoLabeling/blob/HEAD/utils_pseudoLab/wideArchitectures.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":"00e569acd6b45ef0"}},{"code_sha256_prefix":"69b956e680e20587","entry":"conv3x3_wn","repo":"EricArazo/PseudoLabeling","repo_kind":"listed","path":"utils_pseudoLab/PreResNet.py","file_url":"https://github.com/EricArazo/PseudoLabeling/blob/HEAD/utils_pseudoLab/PreResNet.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":"69b956e680e20587"}},{"code_sha256_prefix":"d61da7a79282cec1","entry":"loss_mixup_reg_ep","repo":"EricArazo/PseudoLabeling","repo_kind":"listed","path":"utils_pseudoLab/utils_ssl.py","file_url":"https://github.com/EricArazo/PseudoLabeling/blob/HEAD/utils_pseudoLab/utils_ssl.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":"d61da7a79282cec1"}},{"code_sha256_prefix":"47ef0d9914d9a29e","entry":"loss_soft_reg_ep","repo":"EricArazo/PseudoLabeling","repo_kind":"listed","path":"utils_pseudoLab/utils_ssl.py","file_url":"https://github.com/EricArazo/PseudoLabeling/blob/HEAD/utils_pseudoLab/utils_ssl.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":"47ef0d9914d9a29e"}},{"code_sha256_prefix":"3547e83bd03591ad","entry":"mixup_data","repo":"EricArazo/PseudoLabeling","repo_kind":"listed","path":"utils_pseudoLab/utils_ssl.py","file_url":"https://github.com/EricArazo/PseudoLabeling/blob/HEAD/utils_pseudoLab/utils_ssl.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":"3547e83bd03591ad"}},{"code_sha256_prefix":"c4ccc7ed917575de","entry":"resnet18","repo":"EricArazo/PseudoLabeling","repo_kind":"listed","path":"utils_pseudoLab/ssl_networks.py","file_url":"https://github.com/EricArazo/PseudoLabeling/blob/HEAD/utils_pseudoLab/ssl_networks.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":"c4ccc7ed917575de"}},{"code_sha256_prefix":"99665d4806c9f45a","entry":"resnet18_wndrop","repo":"EricArazo/PseudoLabeling","repo_kind":"listed","path":"utils_pseudoLab/ssl_networks.py","file_url":"https://github.com/EricArazo/PseudoLabeling/blob/HEAD/utils_pseudoLab/ssl_networks.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":"99665d4806c9f45a"}},{"code_sha256_prefix":"9ff47a9283dff48c","entry":"train_val_split","repo":"EricArazo/PseudoLabeling","repo_kind":"listed","path":"cifar10/dataset/cifar10.py","file_url":"https://github.com/EricArazo/PseudoLabeling/blob/HEAD/cifar10/dataset/cifar10.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":"9ff47a9283dff48c"}},{"code_sha256_prefix":"9a9dc60c40303346","entry":"accuracy_v1","repo":"EricArazo/PseudoLabeling","repo_kind":"listed","path":"utils_pseudoLab/utils/criterion.py","file_url":"https://github.com/EricArazo/PseudoLabeling/blob/HEAD/utils_pseudoLab/utils/criterion.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":"9a9dc60c40303346"}},{"code_sha256_prefix":"41f5e551c6aa0cc9","entry":"accuracy_v2","repo":"EricArazo/PseudoLabeling","repo_kind":"listed","path":"utils_pseudoLab/utils/criterion.py","file_url":"https://github.com/EricArazo/PseudoLabeling/blob/HEAD/utils_pseudoLab/utils/criterion.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":"41f5e551c6aa0cc9"}},{"code_sha256_prefix":"4661a82d063bed57","entry":"get_dataset","repo":"EricArazo/PseudoLabeling","repo_kind":"listed","path":"miniImagenet/dataset/miniImagenet.py","file_url":"https://github.com/EricArazo/PseudoLabeling/blob/HEAD/miniImagenet/dataset/miniImagenet.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":"4661a82d063bed57"}},{"code_sha256_prefix":"5b62cd8faeeedbd4","entry":"get_dataset","repo":"EricArazo/PseudoLabeling","repo_kind":"listed","path":"cifar10/dataset/cifar10.py","file_url":"https://github.com/EricArazo/PseudoLabeling/blob/HEAD/cifar10/dataset/cifar10.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":"5b62cd8faeeedbd4"}},{"code_sha256_prefix":"79e2d9d3eaeb6f7f","entry":"get_dataset","repo":"EricArazo/PseudoLabeling","repo_kind":"listed","path":"cifar100/dataset/cifar100.py","file_url":"https://github.com/EricArazo/PseudoLabeling/blob/HEAD/cifar100/dataset/cifar100.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":"79e2d9d3eaeb6f7f"}},{"code_sha256_prefix":"c7ba8abbb7422762","entry":"grouper","repo":"EricArazo/PseudoLabeling","repo_kind":"listed","path":"utils_pseudoLab/TwoSampler.py","file_url":"https://github.com/EricArazo/PseudoLabeling/blob/HEAD/utils_pseudoLab/TwoSampler.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":"c7ba8abbb7422762"}},{"code_sha256_prefix":"9e77e09f4d52e9da","entry":"iterate_eternally","repo":"EricArazo/PseudoLabeling","repo_kind":"listed","path":"utils_pseudoLab/TwoSampler.py","file_url":"https://github.com/EricArazo/PseudoLabeling/blob/HEAD/utils_pseudoLab/TwoSampler.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":"9e77e09f4d52e9da"}},{"code_sha256_prefix":"4232c309adddf9e4","entry":"iterate_once","repo":"EricArazo/PseudoLabeling","repo_kind":"listed","path":"utils_pseudoLab/TwoSampler.py","file_url":"https://github.com/EricArazo/PseudoLabeling/blob/HEAD/utils_pseudoLab/TwoSampler.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":"4232c309adddf9e4"}},{"code_sha256_prefix":"5b666f6b923972fe","entry":"make_dataset","repo":"EricArazo/PseudoLabeling","repo_kind":"listed","path":"miniImagenet/dataset/miniImagenet.py","file_url":"https://github.com/EricArazo/PseudoLabeling/blob/HEAD/miniImagenet/dataset/miniImagenet.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":"5b666f6b923972fe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}