Discriminator Rejection Sampling

by   Samaneh Azadi, et al.
berkeley college

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.


page 8

page 12

page 13

page 14

page 15

page 16


Collaborative GAN Sampling

Generative adversarial networks (GANs) have shown great promise in gener...

Discriminator optimal transport

Within a broad class of generative adversarial networks, we show that di...

Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling

We show that the sum of the implicit generator log-density log p_g of a ...

SocialInteractionGAN: Multi-person Interaction Sequence Generation

Prediction of human actions in social interactions has important applica...

Inception Score, Label Smoothing, Gradient Vanishing and -log(D(x)) Alternative

In this paper, we study several GAN related topics mathematically, inclu...

The Role of ImageNet Classes in Fréchet Inception Distance

Fréchet Inception Distance (FID) is a metric for quantifying the distanc...

Code Repositories


Tensorflow implementation of Discriminator Rejection Sampling

view repo

Please sign up or login with your details

Forgot password? Click here to reset