Discriminator Rejection Sampling

Samaneh Azadi, Catherine Olsson, Trevor Darrell, Ian Goodfellow, Augustus Odena

Abstract:

We propose a rejection sampling scheme using the discriminator of a GAN to
approximately correct errors in the GAN generator distribution. We show that
under quite strict assumptions, this will allow us to recover the data distribution
exactly. We then examine where those strict assumptions break down and design a
practical algorithm—called Discriminator Rejection Sampling (DRS)—that can be
used on real data-sets. Finally, we demonstrate the efficacy of DRS on a mixture of
Gaussians and on the state of the art SAGAN model. On ImageNet, we train an
improved baseline that increases the best published Inception Score from 52.52 to
62.36 and reduces the Frechet Inception Distance from 18.65 to 14.79. We then use
DRS to further improve on this baseline, improving the Inception Score to 76.08
and the FID to 13.75.

Keywords: GANs, rejection sampling

TL;DR: We use a GAN discriminator to perform an approximate rejection sampling scheme on the output of the GAN generator.