{"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/revisiting-semi-supervised-learning-in-the","title":"Revisiting semi-supervised learning in the era of foundation models","arxiv_id":"2503.09707","date":"2025-03-12","proceeding":null,"authors":["Ping Zhang","Zheda Mai","Quang-Huy Nguyen","Wei-Lun Chao"],"abstract":"Semi-supervised learning (SSL) leverages abundant unlabeled data alongside limited labeled data to enhance learning. As vision foundation models (VFMs) increasingly serve as the backbone of vision applications, it remains unclear how SSL interacts with these pre-trained models. To address this gap, we develop new SSL benchmark datasets where frozen VFMs underperform and systematically evaluate representative SSL methods. We make a surprising observation: parameter-efficient fine-tuning (PEFT) using only labeled data often matches SSL performance, even without leveraging unlabeled data. This motivates us to revisit self-training, a conceptually simple SSL baseline, where we use the supervised PEFT model to pseudo-label unlabeled data for further training. To overcome the notorious issue of noisy pseudo-labels, we propose ensembling multiple PEFT approaches and VFM backbones to produce more robust pseudo-labels. Empirical results validate the effectiveness of this simple yet powerful approach, providing actionable insights into SSL with VFMs and paving the way for more scalable and practical semi-supervised learning in the era of foundation models.","url_abs":"https://arxiv.org/abs/2503.09707v1","url_pdf":"https://arxiv.org/pdf/2503.09707v1.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":"revisiting-semi-supervised-learning-in-the","repo_url":"https://github.com/OSU-MLB/SSL-Foundation-Models","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"pseudo-label","task_name":"Pseudo Label"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.09707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09707"}},"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/OSU-MLB/SSL-Foundation-Models","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"official":{"samples":4,"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":"9041c26dbe464d45","entry":"expand_fields","repo":"osu-mlb/ssl-foundation-models","repo_kind":"official","path":"gen_config_pet.py","file_url":"https://github.com/osu-mlb/ssl-foundation-models/blob/HEAD/gen_config_pet.py","link_basis":"first_harvest_node","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":"9041c26dbe464d45"}},{"code_sha256_prefix":"64340821a2d9ddd8","entry":"get_pet_sources","repo":"osu-mlb/ssl-foundation-models","repo_kind":"official","path":"gen_config_pet.py","file_url":"https://github.com/osu-mlb/ssl-foundation-models/blob/HEAD/gen_config_pet.py","link_basis":"first_harvest_node","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":"64340821a2d9ddd8"}},{"code_sha256_prefix":"6b2071ea8351df61","entry":"Hook","repo":"OSU-MLB/SSL-Foundation-Models","repo_kind":"official","path":"semilearn/algorithms/hooks/pseudo_label.py","file_url":"https://github.com/OSU-MLB/SSL-Foundation-Models/blob/HEAD/semilearn/algorithms/hooks/pseudo_label.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":"6b2071ea8351df61"}},{"code_sha256_prefix":"dd08e159932d775a","entry":"PseudoLabelingHook","repo":"OSU-MLB/SSL-Foundation-Models","repo_kind":"official","path":"semilearn/algorithms/hooks/pseudo_label.py","file_url":"https://github.com/OSU-MLB/SSL-Foundation-Models/blob/HEAD/semilearn/algorithms/hooks/pseudo_label.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":"dd08e159932d775a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}