{"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/enhancing-semi-supervised-domain-adaptation","title":"Enhancing Semi-supervised Domain Adaptation via Effective Target Labeling","arxiv_id":null,"date":"2024-03-24","proceeding":"AAAI Conference on Artificial Intelligence 2024 3","authors":["Jiujun He1","Bin Liu1","Guosheng Yin"],"abstract":"Existing semi-supervised domain adaptation (SSDA) models have exhibited impressive performance on the target domain\r\n by effectively utilizing few labeled target samples per class (e.g., 3 samples per class). To guarantee an equal number of\r\n labeled target samples for each class, however, they require domain experts to manually recognize a considerable amount\r\n of the unlabeled target data. Moreover, as the target samples are not equally informative for shaping the decision bound\r\naries of the learning models, it is crucial to select the most informative target samples for labeling, which is, however, impossible for human selectors. As a remedy, we propose an EFfective Target Labeling (EFTL) framework that harnesses active learning and pseudo-labeling strategies to automatically select some informative target samples to annotate. Con\r\ncretely, we introduce a novel sample query strategy, called non-maximal degree node suppression (NDNS), that itera\r\ntively performs maximal degree node query and non-maximal degree node removal to select representative and diverse target samples for labeling. To learn target-specific characteristics, we propose a novel pseudo-labeling strategy that attempts to label low-confidence target samples accurately via clustering consistency (CC), and then inject information of\r\n the model uncertainty into our query process. CC enhances the utilization of the annotation budget and increases the\r\n number of “labeled” target samples while requiring no additional manual effort. Our proposed EFTL framework can\r\n be easily coupled with existing SSDA models, showing significant improvements on three benchmarks.","url_abs":"https://ojs.aaai.org/index.php/AAAI/article/view/29130","url_pdf":"https://ojs.aaai.org/index.php/AAAI/article/view/29130","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":"enhancing-semi-supervised-domain-adaptation","repo_url":"https://github.com/BetterTMrR/EFTL-Pytorch-main","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"semi-supervised-domain-adaptation","task_name":"Semi-supervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}