Wasserstein divergence for GANs

• Main Authors: WU, J., HUANG, Zhiwu, THOMA, J., ACHARYA, D., VAN, Gool L.
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2018
• Subjects: GANs; Progressive growing; Wasserstein divergence; Wasserstein metric; Databases and Information Systems; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/6402; https://ink.library.smu.edu.sg/context/sis_research/article/7405/viewcontent/Wasserstein_Divergence_for_GANs.pdf
• Institution: Singapore Management University

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.