Improving GANs Using Optimal Transport
Lists
Only you see this
Abstract
We present Optimal Transport GAN (OT-GAN), a variant of generative adversarial nets minimizing a new metric measuring the distance between the generator distribution and the data distribution. This metric, which we call mini-batch energy distance, combines optimal transport in primal form with an energy distance defined in an adversarially learned feature space, resulting in a highly discriminative distance function with unbiased mini-batch gradients. Experimentally we show OT-GAN to be highly stable when trained with large mini-batches, and we present state-of-the-art results on several popular benchmark problems for image generation.
BibTeX
@inproceedings{salimans2018improving,
author = {Tim Salimans and Han Zhang and Alec Radford and Dimitris N. Metaxas},
title = {{Improving GANs Using Optimal Transport}},
booktitle = {International Conference on Learning Representations},
year = {2018},
url = {https://openreview.net/forum?id=rkQkBnJAb},
}