{"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/re-evaluating-the-impact-of-unseen-class","title":"Re-Evaluating the Impact of Unseen-Class Unlabeled Data on Semi-Supervised Learning Model","arxiv_id":"2503.00884","date":"2025-03-02","proceeding":null,"authors":["Rundong He","Yicong Dong","LanZhe Guo","Yilong Yin","Tailin Wu"],"abstract":"Semi-supervised learning (SSL) effectively leverages unlabeled data and has been proven successful across various fields. Current safe SSL methods believe that unseen classes in unlabeled data harm the performance of SSL models. However, previous methods for assessing the impact of unseen classes on SSL model performance are flawed. They fix the size of the unlabeled dataset and adjust the proportion of unseen classes within the unlabeled data to assess the impact. This process contravenes the principle of controlling variables. Adjusting the proportion of unseen classes in unlabeled data alters the proportion of seen classes, meaning the decreased classification performance of seen classes may not be due to an increase in unseen class samples in the unlabeled data, but rather a decrease in seen class samples. Thus, the prior flawed assessment standard that ``unseen classes in unlabeled data can damage SSL model performance\" may not always hold true. This paper strictly adheres to the principle of controlling variables, maintaining the proportion of seen classes in unlabeled data while only changing the unseen classes across five critical dimensions, to investigate their impact on SSL models from global robustness and local robustness. Experiments demonstrate that unseen classes in unlabeled data do not necessarily impair the performance of SSL models; in fact, under certain conditions, unseen classes may even enhance them.","url_abs":"https://arxiv.org/abs/2503.00884v1","url_pdf":"https://arxiv.org/pdf/2503.00884v1.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":"re-evaluating-the-impact-of-unseen-class","repo_url":"https://github.com/rundonghe/RESSL","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2503.00884","atlas_url":"https://app.syntology.ai/?focus=2503.00884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.00884"}},"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/rundonghe/RESSL","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"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":"5a340451e2248687","entry":"analyze_data","repo":"rundonghe/RESSL","repo_kind":"official","path":"ana_data.py","file_url":"https://github.com/rundonghe/RESSL/blob/HEAD/ana_data.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5a340451e2248687"}},{"code_sha256_prefix":"db5db838f6e79e1f","entry":"convert_to_rgb","repo":"rundonghe/RESSL","repo_kind":"official","path":"evaluation_unseen_near_change.py","file_url":"https://github.com/rundonghe/RESSL/blob/HEAD/evaluation_unseen_near_change.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"db5db838f6e79e1f"}},{"code_sha256_prefix":"d001ac7997c8d15e","entry":"get_mena_std","repo":"rundonghe/RESSL","repo_kind":"official","path":"evaluation_unseen_class_change.py","file_url":"https://github.com/rundonghe/RESSL/blob/HEAD/evaluation_unseen_class_change.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d001ac7997c8d15e"}},{"code_sha256_prefix":"0d208dd061572549","entry":"imbalance_sample","repo":"rundonghe/RESSL","repo_kind":"official","path":"evaluation_unseen_imbalance.py","file_url":"https://github.com/rundonghe/RESSL/blob/HEAD/evaluation_unseen_imbalance.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0d208dd061572549"}},{"code_sha256_prefix":"cf297d9b65ad7f32","entry":"resize_image","repo":"rundonghe/RESSL","repo_kind":"official","path":"evaluation_unseen_near_change.py","file_url":"https://github.com/rundonghe/RESSL/blob/HEAD/evaluation_unseen_near_change.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cf297d9b65ad7f32"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}