{"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/dash-semi-supervised-learning-with-dynamic","title":"Dash: Semi-Supervised Learning with Dynamic Thresholding","arxiv_id":"2109.00650","date":"2021-09-01","proceeding":null,"authors":["Yi Xu","Lei Shang","Jinxing Ye","Qi Qian","Yu-Feng Li","Baigui Sun","Hao Li","Rong Jin"],"abstract":"While semi-supervised learning (SSL) has received tremendous attentions in many machine learning tasks due to its successful use of unlabeled data, existing SSL algorithms use either all unlabeled examples or the unlabeled examples with a fixed high-confidence prediction during the training progress. However, it is possible that too many correct/wrong pseudo labeled examples are eliminated/selected. In this work we develop a simple yet powerful framework, whose key idea is to select a subset of training examples from the unlabeled data when performing existing SSL methods so that only the unlabeled examples with pseudo labels related to the labeled data will be used to train models. The selection is performed at each updating iteration by only keeping the examples whose losses are smaller than a given threshold that is dynamically adjusted through the iteration. Our proposed approach, Dash, enjoys its adaptivity in terms of unlabeled data selection and its theoretical guarantee. Specifically, we theoretically establish the convergence rate of Dash from the view of non-convex optimization. Finally, we empirically demonstrate the effectiveness of the proposed method in comparison with state-of-the-art over benchmarks.","url_abs":"https://arxiv.org/abs/2109.00650v1","url_pdf":"https://arxiv.org/pdf/2109.00650v1.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":[],"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":"Dash (RA)","rank_in_archive_order":5,"of":27,"metrics":{"Percentage error":"4.56±0.13"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 4000 Labels","model":"Dash (RA, ours)","rank_in_archive_order":9,"of":49,"metrics":{"Percentage error":"4.08±0.06"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-9","task":"Semi-Supervised Image Classification","dataset":"CIFAR-100, 2500 Labels","model":"Dash (RA, WRN-28-8)","rank_in_archive_order":13,"of":16,"metrics":{"Percentage error":"27.18±0.21"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-8","task":"Semi-Supervised Image Classification","dataset":"CIFAR-100, 400 Labels","model":"Dash\n(RA, WRN-28-8)","rank_in_archive_order":18,"of":21,"metrics":{"Percentage error":"44.76±0.96"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-8","task":"Semi-Supervised Image Classification","dataset":"CIFAR-100, 400 Labels","model":"Dash\n(CTA, WRN-28-8)","rank_in_archive_order":19,"of":21,"metrics":{"Percentage error":"44.83±1.36"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-2","task":"Semi-Supervised Image Classification","dataset":"cifar-100, 10000 Labels","model":"Dash (RA, WRN-28-8)","rank_in_archive_order":13,"of":29,"metrics":{"Percentage error":"21.97±0.14"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.00650","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}