One-sided unsupervised domain mapping

Sagie Benaim, Lior Wolf

Research output: Contribution to journalConference articlepeer-review

183 Scopus citations


In unsupervised domain mapping, the learner is given two unmatched datasets A and B. The goal is to learn a mapping GAB that translates a sample in A to the analog sample in B. Recent approaches have shown that when learning simultaneously both GAB and the inverse mapping GBA, convincing mappings are obtained. In this work, we present a method of learning GAB without learning GBA. This is done by learning a mapping that maintains the distance between a pair of samples. Moreover, good mappings are obtained, even by maintaining the distance between different parts of the same sample before and after mapping. We present experimental results that the new method not only allows for one sided mapping learning, but also leads to preferable numerical results over the existing circularity-based constraint. Our entire code is made publicly available at

Original languageEnglish
Pages (from-to)753-763
Number of pages11
JournalAdvances in Neural Information Processing Systems
StatePublished - 2017
Event31st Annual Conference on Neural Information Processing Systems, NIPS 2017 - Long Beach, United States
Duration: 4 Dec 20179 Dec 2017


FundersFunder number
European Metrology Programme for Innovation and ResearchERC CoG 725974
European Research Council


    Dive into the research topics of 'One-sided unsupervised domain mapping'. Together they form a unique fingerprint.

    Cite this