Improving GANs using optimal transport
Captured source
source ↗Improving GANs using optimal transport | OpenAI
March 15, 2018
Improving GANs using optimal transport
Loading…
Share
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.
Authors
Tim Salimans, Han Zhang, Alec Radford, Dimitris Metaxas
Related articles
Hierarchical text-conditional image generation with CLIP latentsPublicationApr 13, 2022
DALL·E: Creating images from textMilestoneJan 5, 2021
Image GPTPublicationJun 17, 2020