Generative Modeling Using the Sliced Wasserstein Distance

Ishan Deshpande, Ziyu Zhang, Alexander Schwing

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Generative Adversarial Nets (GANs) are very successful at modeling distributions from given samples, even in the high-dimensional case. However, their formulation is also known to be hard to optimize and often not stable. While this is particularly true for early GAN formulations, there has been significant empirically motivated and theoretically founded progress to improve stability, for instance, by using the Wasserstein distance rather than the Jenson-Shannon divergence. Here, we consider an alternative formulation for generative modeling based on random projections which, in its simplest form, results in a single objective rather than a saddle-point formulation. By augmenting this approach with a discriminator we improve its accuracy. We found our approach to be significantly more stable compared to even the improved Wasserstein GAN. Further, unlike the traditional GAN loss, the loss formulated in our method is a good measure of the actual distance between the distributions and, for the first time for GAN training, we are able to show estimates for the same.

Original languageEnglish (US)
Title of host publicationProceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
PublisherIEEE Computer Society
Pages3483-3491
Number of pages9
ISBN (Electronic)9781538664209
DOIs
StatePublished - Dec 14 2018
Event31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 - Salt Lake City, United States
Duration: Jun 18 2018Jun 22 2018

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Conference

Conference31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
CountryUnited States
CitySalt Lake City
Period6/18/186/22/18

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Generative Modeling Using the Sliced Wasserstein Distance'. Together they form a unique fingerprint.

  • Cite this

    Deshpande, I., Zhang, Z., & Schwing, A. (2018). Generative Modeling Using the Sliced Wasserstein Distance. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 (pp. 3483-3491). [8578465] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). IEEE Computer Society. https://doi.org/10.1109/CVPR.2018.00367