Wasserstein Divergence for GANs

By Jiqing Wu, Zhiwu Huang, Janine Thoma, Dinesh Acharya, Luc Van Gool. 2017

163 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Luc Van Gool
3. Xiaogang Wang
4. Nicu Sebe
5. Jiashi Feng
6. Ming-Hsuan Yang
7. Yi Yang
8. Chunhua Shen

Citations in the corpus

• Semantics Disentangling for Text-To-Image Generation (2019, background): “A set of constraints are proposed in previous works [28, 16, 26, 9, 36] to improve the training process of GANs, e.”
• Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation (2019, background): “The Wasserstein distance has also recently raised interest in stabilizing generative modeling [1, 14, 73], learning introspective neural networks [32], and obtaining Gaussian mixture models [29] thanks to its geometrically meaningful distance measure even when the supports of the distributions do no”
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications (2020, methodology): “[171] introduce a Wasserstein divergence objective for GANs (WGAN-div), which can faithfully approximate W-div by optimization.”
• DF-GAN: Deep Fusion Generative Adversarial Networks for Text-to-Image Synthesis (2020, background): “For solving this problem, some researches propose the Gradient Penalty [44], [45], [46], [35] and Spectral Normalization [40] which frees WGANs from this challenging constraint in unconditional generation tasks.”