{"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/domain-agnostic-learning-with-disentangled","title":"Domain Agnostic Learning with Disentangled Representations","arxiv_id":"1904.12347","date":"2019-04-28","proceeding":null,"authors":["Xingchao Peng","Zijun Huang","Ximeng Sun","Kate Saenko"],"abstract":"Unsupervised model transfer has the potential to greatly improve the\ngeneralizability of deep models to novel domains. Yet the current literature\nassumes that the separation of target data into distinct domains is known as a\npriori. In this paper, we propose the task of Domain-Agnostic Learning (DAL):\nHow to transfer knowledge from a labeled source domain to unlabeled data from\narbitrary target domains? To tackle this problem, we devise a novel Deep\nAdversarial Disentangled Autoencoder (DADA) capable of disentangling\ndomain-specific features from class identity. We demonstrate experimentally\nthat when the target domain labels are unknown, DADA leads to state-of-the-art\nperformance on several image classification datasets.","url_abs":"http://arxiv.org/abs/1904.12347v1","url_pdf":"http://arxiv.org/pdf/1904.12347v1.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":"domain-agnostic-learning-with-disentangled","repo_url":"https://github.com/VisionLearningGroup/DAL","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"multi-target-domain-adaptation","task_name":"Multi-target Domain Adaptation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-target-domain-adaptation-on-domainnet","task":"Multi-target Domain Adaptation","dataset":"DomainNet","model":"DADA","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"21.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.12347","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}