-
[pdf]
[supp]
[bibtex]@InProceedings{Kavalerov_2021_WACV, author = {Kavalerov, Ilya and Czaja, Wojciech and Chellappa, Rama}, title = {A Multi-Class Hinge Loss for Conditional GANs}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2021}, pages = {1290-1299} }
A Multi-Class Hinge Loss for Conditional GANs
Abstract
We propose a new algorithm to incorporate class conditional information into the critic of GANs via a multi-class generalization of the commonly used Hinge loss that is compatible with both supervised and semi-supervised settings. We study the compromise between training a state of the art generator and an accurate classifier simultaneously, and propose a way to use our algorithm to measure the degree to which a generator and critic are class conditional. We show the trade-off between a generator-critic pair respecting class conditioning inputs and generating the highest quality images. With our multi-hinge loss modification we are able to improve Inception Scores and Frechet Inception Distance on the Imagenet dataset.
Related Material