On the Effectiveness of Least Squares Generative Adversarial Networks

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

93 Scopus Citations
View graph of relations

Author(s)

  • Haoran Xie
  • Zhen Wang
  • Stephen Paul Smolley

Detail(s)

Original languageEnglish
Pages (from-to)2947-2960
Journal / PublicationIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume41
Issue number12
Online published24 Sep 2018
Publication statusPublished - Dec 2019

Abstract

Unsupervised learning with generative adversarial networks (GANs) has proven hugely successful. Regular GANs hypothesize the discriminator as a classifier with the sigmoid cross entropy loss function. However, we found that this loss function may lead to the vanishing gradients problem during the learning process. To overcome such a problem, we propose in this paper the Least Squares Generative Adversarial Networks (LSGANs) which adopt the least squares loss function for the discriminator. We show that minimizing the objective function of LSGAN yields minimizing the Pearson X2 divergence. There are two benefits of LSGANs over regular GANs. First, LSGANs are able to generate higher quality images than regular GANs. Second, LSGANs perform more stable during the learning process. We train LSGANs on several datasets, and the experimental results show that the images generated by LSGANs are of better quality than regular GANs. Furthermore, we evaluate the stability of LSGANs in two groups. One is to compare between LSGANs and regular GANs without gradient penalty. The other one is to compare between LSGANs with gradient penalty and WGANs with gradient penalty. We conduct four experiments to illustrate the stability of LSGANs. The other one is to compare between LSGANs with gradient penalty (LSGANs-GP) and WGANs with gradient penalty (WGANs-GP). The experimental results show that LSGANs-GP succeed in training for all the difficult architectures used in WGANs-GP, including 101-layer ResNet.

Research Area(s)

  • Gallium nitride, Generative adversarial networks, generative model, Generators, image generation, Least squares GANs, Linear programming, Stability analysis, Task analysis, Training, x2 divergence