{"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/one-sided-unsupervised-domain-mapping","title":"One-Sided Unsupervised Domain Mapping","arxiv_id":"1706.00826","date":"2017-06-02","proceeding":"NeurIPS 2017 12","authors":["Sagie Benaim","Lior Wolf"],"abstract":"In unsupervised domain mapping, the learner is given two unmatched datasets\n$A$ and $B$. The goal is to learn a mapping $G_{AB}$ that translates a sample\nin $A$ to the analog sample in $B$. Recent approaches have shown that when\nlearning simultaneously both $G_{AB}$ and the inverse mapping $G_{BA}$,\nconvincing mappings are obtained. In this work, we present a method of learning\n$G_{AB}$ without learning $G_{BA}$. This is done by learning a mapping that\nmaintains the distance between a pair of samples. Moreover, good mappings are\nobtained, even by maintaining the distance between different parts of the same\nsample before and after mapping. We present experimental results that the new\nmethod not only allows for one sided mapping learning, but also leads to\npreferable numerical results over the existing circularity-based constraint.\nOur entire code is made publicly available at\nhttps://github.com/sagiebenaim/DistanceGAN .","url_abs":"http://arxiv.org/abs/1706.00826v2","url_pdf":"http://arxiv.org/pdf/1706.00826v2.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":"one-sided-unsupervised-domain-mapping","repo_url":"https://github.com/sagiebenaim/DistanceGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"style-transfer","task_name":"Style Transfer"},{"task_slug":"unsupervised-image-to-image-translation","task_name":"Unsupervised Image-To-Image Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.00826","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}