{"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/boosting-semi-supervised-learning-by","title":"Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data","arxiv_id":"2303.11066","date":"2023-03-20","proceeding":"CVPR 2023 1","authors":["Yuhao Chen","Xin Tan","Borui Zhao","Zhaowei Chen","RenJie Song","Jiajun Liang","Xuequan Lu"],"abstract":"Semi-supervised learning (SSL) has attracted enormous attention due to its vast potential of mitigating the dependence on large labeled datasets. The latest methods (e.g., FixMatch) use a combination of consistency regularization and pseudo-labeling to achieve remarkable successes. However, these methods all suffer from the waste of complicated examples since all pseudo-labels have to be selected by a high threshold to filter out noisy ones. Hence, the examples with ambiguous predictions will not contribute to the training phase. For better leveraging all unlabeled examples, we propose two novel techniques: Entropy Meaning Loss (EML) and Adaptive Negative Learning (ANL). EML incorporates the prediction distribution of non-target classes into the optimization objective to avoid competition with target class, and thus generating more high-confidence predictions for selecting pseudo-label. ANL introduces the additional negative pseudo-label for all unlabeled data to leverage low-confidence examples. It adaptively allocates this label by dynamically evaluating the top-k performance of the model. EML and ANL do not introduce any additional parameter and hyperparameter. We integrate these techniques with FixMatch, and develop a simple yet powerful framework called FullMatch. Extensive experiments on several common SSL benchmarks (CIFAR-10/100, SVHN, STL-10 and ImageNet) demonstrate that FullMatch exceeds FixMatch by a large margin. Integrated with FlexMatch (an advanced FixMatch-based framework), we achieve state-of-the-art performance. Source code is at https://github.com/megvii-research/FullMatch.","url_abs":"https://arxiv.org/abs/2303.11066v1","url_pdf":"https://arxiv.org/pdf/2303.11066v1.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":"boosting-semi-supervised-learning-by","repo_url":"https://github.com/megvii-research/fullmatch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"pseudo-label","task_name":"Pseudo Label"}],"methods":[{"method_slug":"fixmatch","method_name":"FixMatch"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.11066","atlas_url":"https://app.syntology.ai/?focus=2303.11066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11066"}},"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/megvii-research/fullmatch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/megvii-research/FullMatch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"ran_violates":1,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":"9651662a8cedbe73","entry":"adjust_learning_rate","repo":"megvii-research/FullMatch","repo_kind":"official","path":"train_utils.py","file_url":"https://github.com/megvii-research/FullMatch/blob/HEAD/train_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9651662a8cedbe73"}},{"code_sha256_prefix":"2ed8b93c17cf7375","entry":"net_builder","repo":"megvii-research/FullMatch","repo_kind":"official","path":"utils.py","file_url":"https://github.com/megvii-research/FullMatch/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2ed8b93c17cf7375"}},{"code_sha256_prefix":"6347b368d978a7fd","entry":"sample_labeled_data","repo":"megvii-research/FullMatch","repo_kind":"official","path":"datasets/data_utils.py","file_url":"https://github.com/megvii-research/FullMatch/blob/HEAD/datasets/data_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6347b368d978a7fd"}},{"code_sha256_prefix":"5d7b58a4dd56f54f","entry":"split_ssl_data","repo":"megvii-research/FullMatch","repo_kind":"official","path":"datasets/data_utils.py","file_url":"https://github.com/megvii-research/FullMatch/blob/HEAD/datasets/data_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5d7b58a4dd56f54f"}},{"code_sha256_prefix":"8605dc8a088f3db8","entry":"str2bool","repo":"megvii-research/FullMatch","repo_kind":"official","path":"utils.py","file_url":"https://github.com/megvii-research/FullMatch/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8605dc8a088f3db8"}},{"code_sha256_prefix":"f134f238fbf660cc","entry":"get_logger","repo":"megvii-research/FullMatch","repo_kind":"official","path":"utils.py","file_url":"https://github.com/megvii-research/FullMatch/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f134f238fbf660cc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}