{"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/debiased-learning-from-naturally-imbalanced","title":"Debiased Learning from Naturally Imbalanced Pseudo-Labels","arxiv_id":"2201.01490","date":"2022-01-05","proceeding":"CVPR 2022 1","authors":["Xudong Wang","Zhirong Wu","Long Lian","Stella X. Yu"],"abstract":"Pseudo-labels are confident predictions made on unlabeled target data by a classifier trained on labeled source data. They are widely used for adapting a model to unlabeled data, e.g., in a semi-supervised learning setting. Our key insight is that pseudo-labels are naturally imbalanced due to intrinsic data similarity, even when a model is trained on balanced source data and evaluated on balanced target data. If we address this previously unknown imbalanced classification problem arising from pseudo-labels instead of ground-truth training labels, we could remove model biases towards false majorities created by pseudo-labels. We propose a novel and effective debiased learning method with pseudo-labels, based on counterfactual reasoning and adaptive margins: The former removes the classifier response bias, whereas the latter adjusts the margin of each class according to the imbalance of pseudo-labels. Validated by extensive experimentation, our simple debiased learning delivers significant accuracy gains over the state-of-the-art on ImageNet-1K: 26% for semi-supervised learning with 0.2% annotations and 9% for zero-shot learning. Our code is available at: https://github.com/frank-xwang/debiased-pseudo-labeling.","url_abs":"https://arxiv.org/abs/2201.01490v2","url_pdf":"https://arxiv.org/pdf/2201.01490v2.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":"debiased-learning-from-naturally-imbalanced","repo_url":"https://github.com/frank-xwang/debiased-pseudo-labeling","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"counterfactual-reasoning","task_name":"Counterfactual Reasoning"},{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":null,"task_name":"counterfactual"},{"task_slug":"imbalanced-classification","task_name":"imbalanced classification"}],"methods":[{"method_slug":"fixmatch","method_name":"FixMatch"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-imagenet-0","task":"Few-Shot Image Classification","dataset":"ImageNet - 0-Shot","model":"DebiasPL (ResNet50)","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"68.3%"},"uses_additional_data":true},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-6","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 250 Labels","model":"DebiasPL (w/ FixMatch)","rank_in_archive_order":6,"of":27,"metrics":{"Percentage error":"4.6"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-7","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 40 Labels","model":"DebiasPL (w/ FixMatch)","rank_in_archive_order":7,"of":21,"metrics":{"Percentage error":"5.4"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-16","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 0.2% labeled data","model":"DebiasPL (ResNet-50)","rank_in_archive_order":1,"of":3,"metrics":{"ImageNet Top-1 Accuracy":"69.6%"},"uses_additional_data":true},{"leaderboard":"/sota/semi-supervised-image-classification-on-1","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 1% labeled data","model":"DebiasPL (ResNet-50)","rank_in_archive_order":17,"of":65,"metrics":{"Top 1 Accuracy":"71.3%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2201.01490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.01490"}},"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/frank-xwang/debiased-pseudo-labeling","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/frankxwang/debiased-pseudo-labeling","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"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":"b3b231e13cb2c773","entry":"causal_inference","repo":"frank-xwang/debiased-pseudo-labeling","repo_kind":"official","path":"main_DebiasPL.py","file_url":"https://github.com/frank-xwang/debiased-pseudo-labeling/blob/HEAD/main_DebiasPL.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b3b231e13cb2c773"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}