Improving GANs Using Optimal Transport

Tim Salimans, Han Zhang, Alec Radford, Dimitris Metaxas

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.

TL;DR: An extension of GANs combining optimal transport in primal form with an energy distance defined in an adversarially learned feature space.

Keywords: GAN, generative modeling, adversarial, optimal transport

Code: [ 2 community implementations](https://paperswithcode.com/paper/?openreview=rkQkBnJAb)

Data: [CIFAR-10](https://paperswithcode.com/dataset/cifar-10)

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/improving-gans-using-optimal-transport/code)