02/02/2021

Improved Consistency Regularization for GANs

Zhengli Zhao, Sameer Singh, Honglak Lee, Zizhao Zhang, Augustus Odena, Han Zhang

Keywords:

Abstract Paper Similar 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.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38949200
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 1
 5:21 
 0
 0
 0
 0
 5:12 
 0
 0
 0
 0
 4:54 
 0
 0
 0
 0
 5:06 
 0
 0
 0
 0
 5:00 
 0
 0
 0
 0
 11:37 
 0
 0
 0
 0
 3:01 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 3:25 
 0
 0
 0
 0
 15:23 
 0
 0
 0
 0
 9:28 
 0
 0
 0
 0
 3:18 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 16:57 
 0
 0
 0
 0
 15:55 
 0
 0
 0
 0
 4:41 
 0
 0
 0
 0
 14:44 
 0
 0
 0
 0
 10:22 
 0
 0
 0
 0
 1:59 
 0
 0
 0
 0
 11:33 
 0
 0
 0
 0
 12:02 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 3:03 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 16:11 
 0
 0
 0
 0
 5:03 
 0
 0
 0
 0
 4:54 
 0
 0
 0
 0
 5:11 
 0
 0
 0
 0
 4:25 
 0
 0
 0
 0
 3:14 
 0
 0
 0
 0
 5:48 
 0
 0
 0
 0
 5:23 
 0
 0
 0
 0
 16:17 
 0
 0
 0
 0
 4:05 
 0
 0
 0
 1
 12:43 
 0
 0
 0
 0
 8:00 
 0
 0
 0
 0
 19:54