{"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/unsupervised-domain-adaptation-via-structured","title":"Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling","arxiv_id":"1911.07982","date":"2019-11-18","proceeding":null,"authors":["Qian Wang","Toby P. Breckon"],"abstract":"Unsupervised domain adaptation aims to address the problem of classifying unlabeled samples from the target domain whilst labeled samples are only available from the source domain and the data distributions are different in these two domains. As a result, classifiers trained from labeled samples in the source domain suffer from significant performance drop when directly applied to the samples from the target domain. To address this issue, different approaches have been proposed to learn domain-invariant features or domain-specific classifiers. In either case, the lack of labeled samples in the target domain can be an issue which is usually overcome by pseudo-labeling. Inaccurate pseudo-labeling, however, could result in catastrophic error accumulation during learning. In this paper, we propose a novel selective pseudo-labeling strategy based on structured prediction. The idea of structured prediction is inspired by the fact that samples in the target domain are well clustered within the deep feature space so that unsupervised clustering analysis can be used to facilitate accurate pseudo-labeling. Experimental results on four datasets (i.e. Office-Caltech, Office31, ImageCLEF-DA and Office-Home) validate our approach outperforms contemporary state-of-the-art methods.","url_abs":"https://arxiv.org/abs/1911.07982v1","url_pdf":"https://arxiv.org/pdf/1911.07982v1.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":"unsupervised-domain-adaptation-via-structured","repo_url":"https://github.com/hellowangqian/domain-adaptation-capls","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"structured-prediction","task_name":"Structured Prediction"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-imageclef-da","task":"Domain Adaptation","dataset":"ImageCLEF-DA","model":"SPL","rank_in_archive_order":4,"of":17,"metrics":{"Accuracy":"90.3"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-office-31","task":"Domain Adaptation","dataset":"Office-31","model":"SPL","rank_in_archive_order":18,"of":40,"metrics":{"Average Accuracy":"89.6"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-office-caltech","task":"Domain Adaptation","dataset":"Office-Caltech","model":"SPL","rank_in_archive_order":1,"of":8,"metrics":{"Average Accuracy":"93"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-office-home","task":"Domain Adaptation","dataset":"Office-Home","model":"SPL","rank_in_archive_order":22,"of":29,"metrics":{"Accuracy":"71"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.07982","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}