Real or Not Real, that is the Question

Yuanbo Xiangli, Yubin Deng, Bo Dai, Chen Change Loy, Dahua Lin

Keywords: adversarial, gan, generalization

Mon Session 2 (08:00-10:00 GMT) [Live QA] [Cal]
Mon Session 3 (12:00-14:00 GMT) [Live QA] [Cal]
Monday: Generative models

Abstract: While generative adversarial networks (GAN) have been widely adopted in various topics, in this paper we generalize the standard GAN to a new perspective by treating realness as a random variable that can be estimated from multiple angles. In this generalized framework, referred to as RealnessGAN, the discriminator outputs a distribution as the measure of realness. While RealnessGAN shares similar theoretical guarantees with the standard GAN, it provides more insights on adversarial learning. More importantly, compared to multiple baselines, RealnessGAN provides stronger guidance for the generator, achieving improvements on both synthetic and real-world datasets. Moreover, it enables the basic DCGAN architecture to generate realistic images at 1024*1024 resolution when trained from scratch.

Similar Papers

Smoothness and Stability in GANs
Casey Chu, Kentaro Minami, Kenji Fukumizu,
Consistency Regularization for Generative Adversarial Networks
Han Zhang, Zizhao Zhang, Augustus Odena, Honglak Lee,
Variational Hetero-Encoder Randomized GANs for Joint Image-Text Modeling
Hao Zhang, Bo Chen, Long Tian, Zhengjue Wang, Mingyuan Zhou,