Identifying analogies across domains

Yedid Hoshen, Lior Wolf

Research output: Contribution to conferencePaperpeer-review

7 Scopus citations


Identifying analogies across domains without supervision is an important task for artificial intelligence. Recent advances in cross domain image mapping have concentrated on translating images across domains. Although the progress made is impressive, the visual fidelity many times does not suffice for identifying the matching sample from the other domain. In this paper, we tackle this very task of finding exact analogies between datasets i.e. for every image from domain A find an analogous image in domain B. We present a matching-by-synthesis approach: AN-GAN, and show that it outperforms current techniques. We further show that the cross-domain mapping task can be broken into two parts: domain alignment and learning the mapping function. The tasks can be iteratively solved, and as the alignment is improved, the unsupervised translation function reaches quality comparable to full supervision.

Original languageAmerican English
StatePublished - 2018
Externally publishedYes
Event6th International Conference on Learning Representations, ICLR 2018 - Vancouver, Canada
Duration: 30 Apr 20183 May 2018


Conference6th International Conference on Learning Representations, ICLR 2018

Bibliographical note

Publisher Copyright:
© Learning Representations, ICLR 2018 - Conference Track Proceedings.All right reserved.


Dive into the research topics of 'Identifying analogies across domains'. Together they form a unique fingerprint.

Cite this