{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/cold-paws-unsupervised-class-discovery-and-1","title":"Cold PAWS: Unsupervised class discovery and addressing the cold-start problem for semi-supervised learning","arxiv_id":"2305.10071","date":"2023-05-17","proceeding":null,"authors":["Evelyn J. Mannix","Howard D. Bondell"],"abstract":"In many machine learning applications, labeling datasets can be an arduous and time-consuming task. Although research has shown that semi-supervised learning techniques can achieve high accuracy with very few labels within the field of computer vision, little attention has been given to how images within a dataset should be selected for labeling. In this paper, we propose a novel approach based on well-established self-supervised learning, clustering, and manifold learning techniques that address this challenge of selecting an informative image subset to label in the first instance, which is known as the cold-start or unsupervised selective labelling problem. We test our approach using several publicly available datasets, namely CIFAR10, Imagenette, DeepWeeds, and EuroSAT, and observe improved performance with both supervised and semi-supervised learning strategies when our label selection strategy is used, in comparison to random sampling. We also obtain superior performance for the datasets considered with a much simpler approach compared to other methods in the literature.","url_abs":"https://arxiv.org/abs/2305.10071v2","url_pdf":"https://arxiv.org/pdf/2305.10071v2.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":"cold-paws-unsupervised-class-discovery-and-1","repo_url":"https://github.com/emannix/cold-paws-labelling-selection-strategies","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"cold-paws-unsupervised-class-discovery-and-1","repo_url":"https://github.com/emannix/cold-paws-simclr-and-paws-semi-supervised-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-27","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 100 Labels","model":"SimCLR-kmediods-PAWS","rank_in_archive_order":1,"of":1,"metrics":{"Percentage error":"6.1"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-28","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 30 Labels","model":"SimCLR-kmediods-PAWS","rank_in_archive_order":1,"of":1,"metrics":{"Percentage error":"6.4"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-25","task":"Semi-Supervised Image Classification","dataset":"DeepWeeds, 99 Labels","model":"SimCLR-kmediods-finetuned","rank_in_archive_order":1,"of":1,"metrics":{"Percentage error":"19.6"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-24","task":"Semi-Supervised Image Classification","dataset":"EuroSAT, 100 Labels","model":"SimCLR-kmediods-PAWS","rank_in_archive_order":1,"of":1,"metrics":{"Percentage error":"2.6"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-21","task":"Semi-Supervised Image Classification","dataset":"EuroSAT, 20 Labels","model":"SimCLR-kmediods-PAWS","rank_in_archive_order":1,"of":1,"metrics":{"Percentage error":"3.8"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-23","task":"Semi-Supervised Image Classification","dataset":"Imagenette, 100 Labels","model":"SimCLR-kmediods-PAWS","rank_in_archive_order":1,"of":1,"metrics":{"Percentage error":"6.1"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-22","task":"Semi-Supervised Image Classification","dataset":"Imagenette, 20 Labels","model":"SimCLR-kmediods-PAWS","rank_in_archive_order":1,"of":1,"metrics":{"Percentage error":"10.8"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-cold-2","task":"Semi-Supervised Image Classification (Cold Start)","dataset":"CIFAR-10, 100 Labels","model":"SimCLR-kmediods-PAWS","rank_in_archive_order":1,"of":2,"metrics":{"Percentage error":"6.1"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-cold","task":"Semi-Supervised Image Classification (Cold Start)","dataset":"CIFAR-10, 30 Labels","model":"SimCLR-kmediods-PAWS","rank_in_archive_order":1,"of":1,"metrics":{"Percentage error":"6.4"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-cold-7","task":"Semi-Supervised Image Classification (Cold Start)","dataset":"DeepWeeds, 99 Labels","model":"SimCLR-kmediods-finetuned","rank_in_archive_order":1,"of":1,"metrics":{"Percentage error":"19.6"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-cold-6","task":"Semi-Supervised Image Classification (Cold Start)","dataset":"EuroSAT, 100 Labels","model":"SimCLR-kmediods-PAWS","rank_in_archive_order":1,"of":1,"metrics":{"Percentage error":"2.6"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-cold-3","task":"Semi-Supervised Image Classification (Cold Start)","dataset":"EuroSAT, 20 Labels","model":"SimCLR-kmediods-PAWS","rank_in_archive_order":1,"of":1,"metrics":{"Percentage error":"3.8"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-cold-5","task":"Semi-Supervised Image Classification (Cold Start)","dataset":"Imagenette, 100 Labels","model":"SimCLR-kmediods-PAWS","rank_in_archive_order":1,"of":1,"metrics":{"Percentage error":"6.1"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-cold-4","task":"Semi-Supervised Image Classification (Cold Start)","dataset":"Imagenette, 20 Labels","model":"SimCLR-kmediods-PAWS","rank_in_archive_order":1,"of":1,"metrics":{"Percentage error":"10.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.10071","atlas_url":"https://app.syntology.ai/?focus=2305.10071","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2305.10071"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2305.10071\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2305.10071"},"call":"get_concepts_for_paper(arxiv_id=\"2305.10071\")"}],"by_repo":[{"repo":"emannix/cold-paws-labelling-selection-strategies","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"emannix/cold-paws-simclr-and-paws-semi-supervised-learning","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"4f36368f19b9be9d89b62a70283e2510c1ad53f12ca76c05af0324c9dbcd071a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}