Least Squares Generative Adversarial Networks

Xudong MAO, Qing LI, Haoran XIE, Raymond Y.K. LAU, Zhen WANG, Stephen Paul SMOLLEY

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)

748 Citations (Scopus)

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.
Original languageEnglish
Title of host publicationProceedings of 2017 IEEE International Conference on Computer Vision
PublisherIEEE
Pages2813-2821
Number of pages10
DOIs
Publication statusPublished - Oct 2017
Externally publishedYes
Event2017 IEEE International Conference on Computer Vision (ICCV) - Venice, Venice, Italy
Duration: 22 Oct 201729 Oct 2017
https://www.computer.org/csdl/proceedings/iccv/2017/12OmNAXxXaK

Publication series

NameProceedings : IEEE International Conference on Computer Vision
PublisherIEEE
ISSN (Electronic)2380-7504

Conference

Conference2017 IEEE International Conference on Computer Vision (ICCV)
Abbreviated titleICCV
CountryItaly
CityVenice
Period22/10/1729/10/17
Internet address

Fingerprint Dive into the research topics of 'Least Squares Generative Adversarial Networks'. Together they form a unique fingerprint.

  • Cite this

    MAO, X., LI, Q., XIE, H., LAU, R. Y. K., WANG, Z., & SMOLLEY, S. P. (2017). Least Squares Generative Adversarial Networks. In Proceedings of 2017 IEEE International Conference on Computer Vision (pp. 2813-2821). (Proceedings : IEEE International Conference on Computer Vision). IEEE. https://doi.org/10.1109/ICCV.2017.304