# Unsupervised one to many image translation

Samuel Lavoie-Marchildon
Mikołaj Bińkowski
Aaron Courville
Yoshua Bengio

2018.

Cited by: 1|Views7

Abstract:

We perform completely unsupervised one-sided image to image translation between a source domain and a target domain such that we preserve relevant underlying shared semantics (eg, class, size, shape, etc). In particular, we are interested in a more difficult case than those typically addressed in the literature, where the source and targe...More

Code:

Data:

Get fulltext within 24h
Bibtex