Learning to Discover Cross-Domain Relations with Generative Adversarial Networks

Taeksoo Kim, Moonsu Cha, Hyunsoo Kim, Jung Kwon Lee, Jiwon Kim
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:1857-1865, 2017.

Abstract

While humans easily recognize relations between data from different domains without any supervision, learning to automatically discover them is in general very challenging and needs many ground-truth pairs that illustrate the relations. To avoid costly pairing, we address the task of discovering cross-domain relations given unpaired data. We propose a method based on a generative adversarial network that learns to discover relations between different domains (DiscoGAN). Using the discovered relations, our proposed network successfully transfers style from one domain to another while preserving key attributes such as orientation and face identity.

Cite this Paper

BibTeX
@InProceedings{pmlr-v70-kim17a, title = {Learning to Discover Cross-Domain Relations with Generative Adversarial Networks}, author = {Taeksoo Kim and Moonsu Cha and Hyunsoo Kim and Jung Kwon Lee and Jiwon Kim}, booktitle = {Proceedings of the 34th International Conference on Machine Learning}, pages = {1857--1865}, year = {2017}, editor = {Precup, Doina and Teh, Yee Whye}, volume = {70}, series = {Proceedings of Machine Learning Research}, month = {06--11 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v70/kim17a/kim17a.pdf}, url = {https://proceedings.mlr.press/v70/kim17a.html}, abstract = {While humans easily recognize relations between data from different domains without any supervision, learning to automatically discover them is in general very challenging and needs many ground-truth pairs that illustrate the relations. To avoid costly pairing, we address the task of discovering cross-domain relations given unpaired data. We propose a method based on a generative adversarial network that learns to discover relations between different domains (DiscoGAN). Using the discovered relations, our proposed network successfully transfers style from one domain to another while preserving key attributes such as orientation and face identity.} }
Endnote
%0 Conference Paper %T Learning to Discover Cross-Domain Relations with Generative Adversarial Networks %A Taeksoo Kim %A Moonsu Cha %A Hyunsoo Kim %A Jung Kwon Lee %A Jiwon Kim %B Proceedings of the 34th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Doina Precup %E Yee Whye Teh %F pmlr-v70-kim17a %I PMLR %P 1857--1865 %U https://proceedings.mlr.press/v70/kim17a.html %V 70 %X While humans easily recognize relations between data from different domains without any supervision, learning to automatically discover them is in general very challenging and needs many ground-truth pairs that illustrate the relations. To avoid costly pairing, we address the task of discovering cross-domain relations given unpaired data. We propose a method based on a generative adversarial network that learns to discover relations between different domains (DiscoGAN). Using the discovered relations, our proposed network successfully transfers style from one domain to another while preserving key attributes such as orientation and face identity.
APA
Kim, T., Cha, M., Kim, H., Lee, J.K. & Kim, J.. (2017). Learning to Discover Cross-Domain Relations with Generative Adversarial Networks. Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research 70:1857-1865 Available from https://proceedings.mlr.press/v70/kim17a.html.

Related Material