Improved Consistency Regularization for GANs

Citations Over TimeTop 10% of 2021 papers

Abstract

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.

Related Papers

• → Constraint tightness and looseness versus local and global consistency(1997)57 cited
• → A strong local consistency for constraint satisfaction(2003)14 cited
• → Image Transformation Based on Generative Adversarial Networks(2019)1 cited
• → Learning to navigate image manifolds induced by generative adversarial networks for unsupervised video generation(2019)
• → Learning to navigate image manifolds induced by generative adversarial\n networks for unsupervised video generation(2019)