{"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/conmatch-semi-supervised-learning-with","title":"ConMatch: Semi-Supervised Learning with Confidence-Guided Consistency Regularization","arxiv_id":"2208.08631","date":"2022-08-18","proceeding":null,"authors":["Jiwon Kim","Youngjo Min","Daehwan Kim","Gyuseong Lee","Junyoung Seo","Kwangrok Ryoo","Seungryong Kim"],"abstract":"We present a novel semi-supervised learning framework that intelligently leverages the consistency regularization between the model's predictions from two strongly-augmented views of an image, weighted by a confidence of pseudo-label, dubbed ConMatch. While the latest semi-supervised learning methods use weakly- and strongly-augmented views of an image to define a directional consistency loss, how to define such direction for the consistency regularization between two strongly-augmented views remains unexplored. To account for this, we present novel confidence measures for pseudo-labels from strongly-augmented views by means of weakly-augmented view as an anchor in non-parametric and parametric approaches. Especially, in parametric approach, we present, for the first time, to learn the confidence of pseudo-label within the networks, which is learned with backbone model in an end-to-end manner. In addition, we also present a stage-wise training to boost the convergence of training. When incorporated in existing semi-supervised learners, ConMatch consistently boosts the performance. We conduct experiments to demonstrate the effectiveness of our ConMatch over the latest methods and provide extensive ablation studies. Code has been made publicly available at https://github.com/JiwonCocoder/ConMatch.","url_abs":"https://arxiv.org/abs/2208.08631v2","url_pdf":"https://arxiv.org/pdf/2208.08631v2.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":"conmatch-semi-supervised-learning-with","repo_url":"https://github.com/jiwoncocoder/conmatch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"pseudo-label","task_name":"Pseudo Label"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2208.08631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.08631"}},"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/jiwoncocoder/conmatch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/JiwonCocoder/ConMatch","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_violates":1,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"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":"bd72ec778a0fefb6","entry":"Con_estimator","repo":"JiwonCocoder/ConMatch","repo_kind":"official","path":"models/conmatch/conmatch.py","file_url":"https://github.com/JiwonCocoder/ConMatch/blob/HEAD/models/conmatch/conmatch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd72ec778a0fefb6"}},{"code_sha256_prefix":"de8138352ac891f6","entry":"custom_replace","repo":"JiwonCocoder/ConMatch","repo_kind":"official","path":"models/conmatch/conmatch.py","file_url":"https://github.com/JiwonCocoder/ConMatch/blob/HEAD/models/conmatch/conmatch.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"de8138352ac891f6"}},{"code_sha256_prefix":"0715822781228320","entry":"ConMatch2","repo":"JiwonCocoder/ConMatch","repo_kind":"official","path":"models/conmatch/conmatch.py","file_url":"https://github.com/JiwonCocoder/ConMatch/blob/HEAD/models/conmatch/conmatch.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":"0715822781228320"}},{"code_sha256_prefix":"bcba2fa5f9a199a7","entry":"estimate_metric_binary_2","repo":"JiwonCocoder/ConMatch","repo_kind":"official","path":"models/conmatch/conmatch.py","file_url":"https://github.com/JiwonCocoder/ConMatch/blob/HEAD/models/conmatch/conmatch.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":"bcba2fa5f9a199a7"}},{"code_sha256_prefix":"fb2d176308e0293d","entry":"estimate_metric_binary_con_eval","repo":"JiwonCocoder/ConMatch","repo_kind":"official","path":"models/conmatch/conmatch.py","file_url":"https://github.com/JiwonCocoder/ConMatch/blob/HEAD/models/conmatch/conmatch.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":"fb2d176308e0293d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}