{"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/looking-back-at-labels-a-class-based-domain","title":"Looking back at Labels: A Class based Domain Adaptation Technique","arxiv_id":"1904.01341","date":"2019-04-02","proceeding":null,"authors":["Vinod Kumar Kurmi","Vinay P. Namboodiri"],"abstract":"In this paper, we solve the problem of adapting classifiers across domains.\nWe consider the problem of domain adaptation for multi-class classification\nwhere we are provided a labeled set of examples in a source dataset and we are\nprovided a target dataset with no supervision. In this setting, we propose an\nadversarial discriminator based approach. While the approach based on\nadversarial discriminator has been previously proposed; in this paper, we\npresent an informed adversarial discriminator. Our observation relies on the\nanalysis that shows that if the discriminator has access to all the information\navailable including the class structure present in the source dataset, then it\ncan guide the transformation of features of the target set of classes to a more\nstructure adapted space. Using this formulation, we obtain state-of-the-art\nresults for the standard evaluation on benchmark datasets. We further provide\ndetailed analysis which shows that using all the labeled information results in\nan improved domain adaptation.","url_abs":"http://arxiv.org/abs/1904.01341v1","url_pdf":"http://arxiv.org/pdf/1904.01341v1.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":"looking-back-at-labels-a-class-based-domain","repo_url":"https://github.com/vinodkkurmi/DiscriminatorDomainAdaptation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"multi-class-classification","task_name":"Multi-class Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-imageclef-da","task":"Domain Adaptation","dataset":"ImageCLEF-DA","model":"IDDA (Alexnet)","rank_in_archive_order":15,"of":17,"metrics":{"Accuracy":"80.6"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-office-31","task":"Domain Adaptation","dataset":"Office-31","model":"IDDA(Alexnet)","rank_in_archive_order":36,"of":40,"metrics":{"Average Accuracy":"78.5"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-office-31","task":"Domain Adaptation","dataset":"Office-31","model":"IDDA (AlexNet)","rank_in_archive_order":37,"of":40,"metrics":{"Average Accuracy":"78.5"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-office-home","task":"Domain Adaptation","dataset":"Office-Home","model":"IDDA","rank_in_archive_order":28,"of":29,"metrics":{"Accuracy":"49.46"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.01341","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}