{"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/joint-domain-alignment-and-discriminative","title":"Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation","arxiv_id":"1808.09347","date":"2018-08-28","proceeding":null,"authors":["Chao Chen","Zhihong Chen","Boyuan Jiang","Xinyu Jin"],"abstract":"Recently, considerable effort has been devoted to deep domain adaptation in\ncomputer vision and machine learning communities. However, most of existing\nwork only concentrates on learning shared feature representation by minimizing\nthe distribution discrepancy across different domains. Due to the fact that all\nthe domain alignment approaches can only reduce, but not remove the domain\nshift. Target domain samples distributed near the edge of the clusters, or far\nfrom their corresponding class centers are easily to be misclassified by the\nhyperplane learned from the source domain. To alleviate this issue, we propose\nto joint domain alignment and discriminative feature learning, which could\nbenefit both domain alignment and final classification. Specifically, an\ninstance-based discriminative feature learning method and a center-based\ndiscriminative feature learning method are proposed, both of which guarantee\nthe domain invariant features with better intra-class compactness and\ninter-class separability. Extensive experiments show that learning the\ndiscriminative features in the shared feature space can significantly boost the\nperformance of deep domain adaptation methods.","url_abs":"http://arxiv.org/abs/1808.09347v2","url_pdf":"http://arxiv.org/pdf/1808.09347v2.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":"joint-domain-alignment-and-discriminative","repo_url":"https://github.com/chenchao666/JDDA-Master","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1808.09347","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}