{"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/confidence-regularized-self-training","title":"Confidence Regularized Self-Training","arxiv_id":"1908.09822","date":"2019-08-26","proceeding":"ICCV 2019 10","authors":["Yang Zou","Zhiding Yu","Xiaofeng Liu","B. V. K. Vijaya Kumar","Jinsong Wang"],"abstract":"Recent advances in domain adaptation show that deep self-training presents a powerful means for unsupervised domain adaptation. These methods often involve an iterative process of predicting on target domain and then taking the confident predictions as pseudo-labels for retraining. However, since pseudo-labels can be noisy, self-training can put overconfident label belief on wrong classes, leading to deviated solutions with propagated errors. To address the problem, we propose a confidence regularized self-training (CRST) framework, formulated as regularized self-training. Our method treats pseudo-labels as continuous latent variables jointly optimized via alternating optimization. We propose two types of confidence regularization: label regularization (LR) and model regularization (MR). CRST-LR generates soft pseudo-labels while CRST-MR encourages the smoothness on network output. Extensive experiments on image classification and semantic segmentation show that CRSTs outperform their non-regularized counterpart with state-of-the-art performance. The code and models of this work are available at https://github.com/yzou2/CRST.","url_abs":"https://arxiv.org/abs/1908.09822v3","url_pdf":"https://arxiv.org/pdf/1908.09822v3.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":"confidence-regularized-self-training","repo_url":"https://github.com/yzou2/CRST","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"confidence-regularized-self-training","repo_url":"https://github.com/yzou2/CBST","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"synthetic-to-real-translation","task_name":"Synthetic-to-Real Translation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-office-31","task":"Domain Adaptation","dataset":"Office-31","model":"MRKLD + LRENT","rank_in_archive_order":26,"of":40,"metrics":{"Average Accuracy":"86.8"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-visda2017","task":"Domain Adaptation","dataset":"VisDA2017","model":"MRKLD + LRENT","rank_in_archive_order":21,"of":28,"metrics":{"Accuracy":"78.1"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-visda2017","task":"Domain Adaptation","dataset":"VisDA2017","model":"CRST","rank_in_archive_order":22,"of":28,"metrics":{"Accuracy":"78.1"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-synthia-to","task":"Image-to-Image Translation","dataset":"SYNTHIA-to-Cityscapes","model":"LRENT (DeepLabv2)","rank_in_archive_order":18,"of":28,"metrics":{"mIoU (13 classes)":"48.7"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-densepass","task":"Semantic Segmentation","dataset":"DensePASS","model":"CRST","rank_in_archive_order":24,"of":36,"metrics":{"mIoU":"31.67%"},"uses_additional_data":false},{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","task":"Synthetic-to-Real Translation","dataset":"GTAV-to-Cityscapes Labels","model":"CRST(MRKLD-SP-MST)","rank_in_archive_order":50,"of":73,"metrics":{"mIoU":"49.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1908.09822","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.09822"}},"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/yzou2/CBST","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yzou2/CRST","reach":null}],"summary":{"ran_fixture":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":1,"samples":[{"code_sha256_prefix":"90009a990acf6c4d","entry":"colorize_mask","repo":"yzou2/CRST","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/yzou2/CRST/blob/HEAD/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"90009a990acf6c4d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}