Improved Consistency Regularization for GANs

by   Zhengli Zhao, et al.

Recent work has increased the performance of Generative Adversarial Networks (GANs) by enforcing a consistency cost on the discriminator. We improve on this technique in several ways. We first show that consistency regularization can introduce artifacts into the GAN samples and explain how to fix this issue. We then propose several modifications to the consistency regularization procedure designed to improve its performance. We carry out extensive experiments quantifying the benefit of our improvements. For unconditional image synthesis on CIFAR-10 and CelebA, our modifications yield the best known FID scores on various GAN architectures. For conditional image synthesis on CIFAR-10, we improve the state-of-the-art FID score from 11.48 to 9.21. Finally, on ImageNet-2012, we apply our technique to the original BigGAN model and improve the FID from 6.66 to 5.38, which is the best score at that model size.


page 7

page 12

page 13


Consistency Regularization for Generative Adversarial Networks

Generative Adversarial Networks (GANs) are known to be difficult to trai...

Consistency Regularization with Generative Adversarial Networks for Semi-Supervised Image Classification

Generative Adversarial Networks (GANs) based semi-supervised learning (S...

Image Augmentations for GAN Training

Data augmentations have been widely studied to improve the accuracy and ...

Efficient Subsampling for Generating High-Quality Images from Conditional Generative Adversarial Networks

Subsampling unconditional generative adversarial networks (GANs) to impr...

Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation

Unpaired image-to-image (I2I) translation has received considerable atte...

Feature Statistics Mixing Regularization for Generative Adversarial Networks

In generative adversarial networks, improving discriminators is one of t...

Lower Dimensional Kernels for Video Discriminators

This work presents an analysis of the discriminators used in Generative ...

Please sign up or login with your details

Forgot password? Click here to reset