Keywords: GAN, generative modeling, adversarial, optimal transport
TL;DR: An extension of GANs combining optimal transport in primal form with an energy distance defined in an adversarially learned feature space.
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.
Code: [![Papers with Code](/images/pwc_icon.svg) 2 community implementations](https://paperswithcode.com/paper/?openreview=rkQkBnJAb)