A Multi-Class Hinge Loss for Conditional GANs

Ilya Kavalerov, Wojciech Czaja, Rama Chellappa

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.
BibTeX
@inproceedings{kavalerov2021multi,
  author = {Ilya Kavalerov and Wojciech Czaja and Rama Chellappa},
  title = {{A Multi-Class Hinge Loss for Conditional GANs}},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
  year = {2021},
  doi = {10.1109/wacv48630.2021.00133},
}

Loading related content...

Figure