Least Squares Generative Adversarial Networks

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)

848 Scopus Citations
View graph of relations

Author(s)

  • Haoran Xie
  • Zhen Wang
  • Stephen Paul Smolley

Detail(s)

Original languageEnglish
Title of host publicationProceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2813-2821
ISBN (Electronic)9781538610329
ISBN (Print)9781538610336
Publication statusPublished - Oct 2017

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
Volume2017
ISSN (Print)1550-5499
ISSN (Electronic)2380-7504

Conference

TitleICCV 2017 : International Conference on Computer Vision
PlaceItaly
CityVenice
Period22 - 29 October 2017

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 evaluate LSGANs on LSUN and CIFAR-10 datasets and the experimental results show that the images generated by LSGANs are of better quality than the ones generated by regular GANs. We also conduct two comparison experiments between LSGANs and regular GANs to illustrate the stability of LSGANs.

Citation Format(s)

Least Squares Generative Adversarial Networks. / Mao, Xudong; Li, Qing; Xie, Haoran; Lau, Raymond Y.K.; Wang, Zhen; Smolley, Stephen Paul.

Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 2813-2821 8237566 (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2017).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)