Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

9-2018

Abstract

In many domains of computer vision, generative adversarial networks (GANs) have achieved great success, among which the family of Wasserstein GANs (WGANs) is considered to be state-of-the-art due to the theoretical contributions and competitive qualitative performance. However, it is very challenging to approximate the k-Lipschitz constraint required by the Wasserstein-1 metric (W-met). In this paper, we propose a novel Wasserstein divergence (W-div), which is a relaxed version of W-met and does not require the k-Lipschitz constraint. As a concrete application, we introduce a Wasserstein divergence objective for GANs (WGAN-div), which can faithfully approximate W-div through optimization. Under various settings, including progressive growing training, we demonstrate the stability of the proposed WGAN-div owing to its theoretical and practical advantages over WGANs. Also, we study the quantitative and visual performance of WGAN-div on standard image synthesis benchmarks, showing the superior performance of WGAN-div compared to the state-of-the-art methods.

Keywords

GANs; Progressive growing; Wasserstein divergence; Wasserstein metric

Discipline

Databases and Information Systems | Graphics and Human Computer Interfaces

Research Areas

Data Science and Engineering

Publication

Proceedings of the 15th European Conference on Computer Vision, (ECCV) 2018, Munich, Germany, September 8-14

Volume

11209

First Page

673

Last Page

688

ISBN

9783030012274

Identifier

10.1007/978-3-030-01228-1_40

Publisher

Springer Nature

City or Country

Switzerland

Download

Share

COinS