Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

6-2019

Abstract

In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions. Unfortunately, it is challenging to approximate the WD of high-dimensional distributions. In contrast, the sliced Wasserstein distance (SWD) factorizes high-dimensional distributions into their multiple one-dimensional marginal distributions and is thus easier to approximate. In this paper, we introduce novel approximations of the primal and dual SWD. Instead of using a large number of random projections, as it is done by conventional SWD approximation methods, we propose to approximate SWDs with a small number of parameterized orthogonal projections in an end-to-end deep learning fashion. As concrete applications of our SWD approximations, we design two types of differentiable SWD blocks to equip modern generative frameworks---Auto-Encoders (AE) and Generative Adversarial Networks (GAN). In the experiments, we not only show the superiority of the proposed generative models on standard image synthesis benchmarks, but also demonstrate the state-of-the-art performance on challenging high resolution image and video generation in an unsupervised manner.

Keywords

Deep Learning, Image and Video Synthesis, Optimization Methods

Discipline

Databases and Information Systems | Graphics and Human Computer Interfaces

Research Areas

Data Science and Engineering

Publication

2019 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019: Long Beach, CA, June 16-21: Proceedings

First Page

3708

Last Page

3717

ISBN

9781728132938

Identifier

10.1109/CVPR.2019.00383

Publisher

IEEE Computer Society

City or Country

Los Alamitos, CA

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1109/CVPR.2019.00383

Download

Share

COinS