Improving sample diversity of a pre-trained, class-conditional GAN by changing its class embeddings

10/10/2019 ∙ by Qi Li, et al. ∙ 22

Mode collapse is a well-known issue with Generative Adversarial Networks (GANs) and is a byproduct of unstable GAN training. We propose to improve the sample diversity of a pre-trained class-conditional generator by modifying its class embeddings in the direction of maximizing the log probability outputs of a classifier pre-trained on the same dataset. We improved the sample diversity of state-of-the-art ImageNet BigGANs at both 128x128 and 256x256 resolutions. By replacing the embeddings, we can also synthesize plausible images for Places365 using a BigGAN pre-trained on ImageNet.



There are no comments yet.


page 15

page 16

page 17

page 20

page 24

page 26

page 27

page 31

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.