Rethinking the Truly Unsupervised Image-to-Image Translation
Lists
Only you see this
Abstract
Every recent image-to-image translation model uses either image-level (i.e. input-output pairs) or set-level (i.e. domain labels) supervision at a minimum. However, even the set-level supervision can be a serious bottleneck for data collection in practice. In this paper, we tackle image-to-image translation in a fully unsupervised setting, i.e., neither paired images nor domain labels. To this end, we propose a truly unsupervised image-to-image translation model (TUNIT) that simultaneously learns to separate image domains and translate input images into the estimated domains. Experimental results show that our model achieves comparable or even better performance than the set-level supervised model trained with full labels, generalizes well on various datasets, and is robust against the choice of hyperparameters (e.g. the preset number of pseudo domains). In addition, TUNIT extends well to the semi-supervised scenario with various amount of labels provided.
BibTeX
@inproceedings{baek2020rethinking,
author = {Kyungjune Baek and Yunjey Choi and Youngjung Uh and Jaejun Yoo and Hyunjung Shim},
title = {{Rethinking the Truly Unsupervised Image-to-Image Translation}},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2020},
doi = {10.1109/iccv48922.2021.01389},
}