Max-sliced wasserstein distance and its use for gans

Ishan Deshpande, Yuan Ting Hu, Ruoyu Sun, Ayis Pyrros, Nasir Siddiqui, Sanmi Koyejo, Zhizhen Zhao, David Forsyth, Alexander G. Schwing

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

Abstract

Generative adversarial nets (GANs) and variational auto-encoders have significantly improved our distribution modeling capabilities, showing promise for dataset augmentation, image-to-image translation and feature learning. However, to model high-dimensional distributions, sequential training and stacked architectures are common, increasing the number of tunable hyper-parameters as well as the training time. Nonetheless, the sample complexity of the distance metrics remains one of the factors affecting GAN training. We first show that the recently proposed sliced Wasserstein distance has compelling sample complexity properties when compared to the Wasserstein distance. To further improve the sliced Wasserstein distance we then analyze its 'projection complexity' and develop the max-sliced Wasserstein distance which enjoys compelling sample complexity while reducing projection complexity, albeit necessitating a max estimation. We finally illustrate that the proposed distance trains GANs on high-dimensional images up to a resolution of 256x256 easily.

Original languageEnglish (US)
Title of host publicationProceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
PublisherIEEE Computer Society
Pages10640-10648
Number of pages9
ISBN (Electronic)9781728132938
DOIs
StatePublished - Jun 2019
Event32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 - Long Beach, United States
Duration: Jun 16 2019Jun 20 2019

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2019-June
ISSN (Print)1063-6919

Conference

Conference32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
CountryUnited States
CityLong Beach
Period6/16/196/20/19

Keywords

  • Deep Learning

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Deshpande, I., Hu, Y. T., Sun, R., Pyrros, A., Siddiqui, N., Koyejo, S., Zhao, Z., Forsyth, D., & Schwing, A. G. (2019). Max-sliced wasserstein distance and its use for gans. In Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 (pp. 10640-10648). [8953668] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2019-June). IEEE Computer Society. https://doi.org/10.1109/CVPR.2019.01090