{"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/doublematch-improving-semi-supervised","title":"DoubleMatch: Improving Semi-Supervised Learning with Self-Supervision","arxiv_id":"2205.05575","date":"2022-05-11","proceeding":null,"authors":["Erik Wallin","Lennart Svensson","Fredrik Kahl","Lars Hammarstrand"],"abstract":"Following the success of supervised learning, semi-supervised learning (SSL) is now becoming increasingly popular. SSL is a family of methods, which in addition to a labeled training set, also use a sizable collection of unlabeled data for fitting a model. Most of the recent successful SSL methods are based on pseudo-labeling approaches: letting confident model predictions act as training labels. While these methods have shown impressive results on many benchmark datasets, a drawback of this approach is that not all unlabeled data are used during training. We propose a new SSL algorithm, DoubleMatch, which combines the pseudo-labeling technique with a self-supervised loss, enabling the model to utilize all unlabeled data in the training process. We show that this method achieves state-of-the-art accuracies on multiple benchmark datasets while also reducing training times compared to existing SSL methods. Code is available at https://github.com/walline/doublematch.","url_abs":"https://arxiv.org/abs/2205.05575v1","url_pdf":"https://arxiv.org/pdf/2205.05575v1.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":"doublematch-improving-semi-supervised","repo_url":"https://github.com/walline/doublematch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-6","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 250 Labels","model":"DoubleMatch","rank_in_archive_order":18,"of":27,"metrics":{"Percentage error":"5.56±0.42"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-7","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 40 Labels","model":"DoubleMatch","rank_in_archive_order":19,"of":21,"metrics":{"Percentage error":"13.59±5.60"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 4000 Labels","model":"DoubleMatch","rank_in_archive_order":20,"of":49,"metrics":{"Percentage error":"4.65±0.17"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-9","task":"Semi-Supervised Image Classification","dataset":"CIFAR-100, 2500 Labels","model":"DoubleMatch","rank_in_archive_order":12,"of":16,"metrics":{"Percentage error":"27.07± 0.26"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-8","task":"Semi-Supervised Image Classification","dataset":"CIFAR-100, 400 Labels","model":"DoubleMatch","rank_in_archive_order":14,"of":21,"metrics":{"Percentage error":"41.83± 1.22"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-stl-1","task":"Semi-Supervised Image Classification","dataset":"STL-10, 1000 Labels","model":"DoubleMatch","rank_in_archive_order":4,"of":13,"metrics":{"Accuracy":"95.65±0.20"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-svhn","task":"Semi-Supervised Image Classification","dataset":"SVHN, 1000 labels","model":"DoubleMatch","rank_in_archive_order":2,"of":17,"metrics":{"Accuracy":"97.90 ± 0.07"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-svhn-1","task":"Semi-Supervised Image Classification","dataset":"SVHN, 250 Labels","model":"DoubleMatch","rank_in_archive_order":3,"of":15,"metrics":{"Accuracy":"97.63±0.35"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-svhn-2","task":"Semi-Supervised Image Classification","dataset":"SVHN, 40 Labels","model":"DoubleMatch","rank_in_archive_order":5,"of":5,"metrics":{"Percentage error":"15.37±11.81"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-2","task":"Semi-Supervised Image Classification","dataset":"cifar-100, 10000 Labels","model":"DoubleMatch","rank_in_archive_order":7,"of":29,"metrics":{"Percentage error":"21.22± 0.17"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.05575","atlas_url":"https://app.syntology.ai/?focus=2205.05575","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":"2205.05575"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2205.05575\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2205.05575"},"call":"get_concepts_for_paper(arxiv_id=\"2205.05575\")"}],"by_repo":[{"repo":"walline/doublematch","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":"6a5ed5035123f3657955a85b4a076bd6e720998185bca38f9af7182dd8fbb7a0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}