{"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/nam-non-adversarial-unsupervised-domain","title":"NAM: Non-Adversarial Unsupervised Domain Mapping","arxiv_id":"1806.00804","date":"2018-06-03","proceeding":"ECCV 2018 9","authors":["Yedid Hoshen","Lior Wolf"],"abstract":"Several methods were recently proposed for the task of translating images\nbetween domains without prior knowledge in the form of correspondences. The\nexisting methods apply adversarial learning to ensure that the distribution of\nthe mapped source domain is indistinguishable from the target domain, which\nsuffers from known stability issues. In addition, most methods rely heavily on\n`cycle' relationships between the domains, which enforce a one-to-one mapping.\nIn this work, we introduce an alternative method: Non-Adversarial Mapping\n(NAM), which separates the task of target domain generative modeling from the\ncross-domain mapping task. NAM relies on a pre-trained generative model of the\ntarget domain, and aligns each source image with an image synthesized from the\ntarget domain, while jointly optimizing the domain mapping function. It has\nseveral key advantages: higher quality and resolution image translations,\nsimpler and more stable training and reusable target models. Extensive\nexperiments are presented validating the advantages of our method.","url_abs":"http://arxiv.org/abs/1806.00804v2","url_pdf":"http://arxiv.org/pdf/1806.00804v2.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":"nam-non-adversarial-unsupervised-domain","repo_url":"https://github.com/facebookresearch/NAM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}