2000 character limit reached
Discriminator optimal transport
Published 15 Oct 2019 in stat.ML, cs.LG, and eess.IV | (1910.06832v3)
Abstract: Within a broad class of generative adversarial networks, we show that discriminator optimization process increases a lower bound of the dual cost function for the Wasserstein distance between the target distribution and the generator distribution . It implies that the trained discriminator can approximate optimal transport (OT) from to .Based on some experiments and a bit of OT theory, we propose a discriminator optimal transport (DOT) scheme to improve generated images. We show that it improves inception score and FID calculated by un-conditional GAN trained by CIFAR-10, STL-10 and a public pre-trained model of conditional GAN by ImageNet.
Paper Prompts
Sign up for free to create and run prompts on this paper.