Consistency Regularization for Generative Adversarial Networks

by   Han Zhang, et al.

Generative Adversarial Networks (GANs) are known to be difficult to train, despite considerable research effort. Several regularization techniques for stabilizing training have been proposed, but they introduce non-trivial computational overheads and interact poorly with existing techniques like spectral normalization. In this work, we propose a simple, effective training stabilizer based on the notion of consistency regularization—a popular technique in the semi-supervised learning literature. In particular, we augment data passing into the GAN discriminator and penalize the sensitivity of the discriminator to these augmentations. We conduct a series of experiments to demonstrate that consistency regularization works effectively with spectral normalization and various GAN architectures, loss functions and optimizer settings. Our method achieves the best FID scores for unconditional image generation compared to other regularization methods on CIFAR-10 and CelebA. Moreover, Our consistency regularized GAN (CR-GAN) improves state-of-the-art FID scores for conditional generation from 14.73 to 11.67 on CIFAR-10 and from 8.73 to 6.66 on ImageNet-2012.


page 13

page 14

page 15

page 16


Improved Consistency Regularization for GANs

Recent work has increased the performance of Generative Adversarial Netw...

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

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

Feature Statistics Mixing Regularization for Generative Adversarial Networks

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

GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks

Modern generative adversarial networks (GANs) predominantly use piecewis...

ViTGAN: Training GANs with Vision Transformers

Recently, Vision Transformers (ViTs) have shown competitive performance ...

Whitening and Coloring transform for GANs

Batch Normalization (BN) is a common technique used both in discriminati...

The GAN Landscape: Losses, Architectures, Regularization, and Normalization

Generative Adversarial Networks (GANs) are a class of deep generative mo...

Please sign up or login with your details

Forgot password? Click here to reset