{"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/simultaneous-deep-transfer-across-domains-and","title":"Simultaneous Deep Transfer Across Domains and Tasks","arxiv_id":"1510.02192","date":"2015-10-08","proceeding":"ICCV 2015 12","authors":["Eric Tzeng","Judy Hoffman","Trevor Darrell","Kate Saenko"],"abstract":"Recent reports suggest that a generic supervised deep CNN model trained on a\nlarge-scale dataset reduces, but does not remove, dataset bias. Fine-tuning\ndeep models in a new domain can require a significant amount of labeled data,\nwhich for many applications is simply not available. We propose a new CNN\narchitecture to exploit unlabeled and sparsely labeled target domain data. Our\napproach simultaneously optimizes for domain invariance to facilitate domain\ntransfer and uses a soft label distribution matching loss to transfer\ninformation between tasks. Our proposed adaptation method offers empirical\nperformance which exceeds previously published results on two standard\nbenchmark visual domain adaptation tasks, evaluated across supervised and\nsemi-supervised adaptation settings.","url_abs":"http://arxiv.org/abs/1510.02192v1","url_pdf":"http://arxiv.org/pdf/1510.02192v1.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":"simultaneous-deep-transfer-across-domains-and","repo_url":"https://github.com/mahfujau/domain_adaptation_iccv15","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1510.02192","atlas_url":"https://app.syntology.ai/?focus=1510.02192","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}