paper-with-me

Papers

Wasserstein Divergence for GANs

2017-12-04 · ECCV 2018 9 · Jiqing Wu, Zhiwu Huang, Janine Thoma, Dinesh Acharya, Luc van Gool

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 of computer vision, showing the superior performance of WGAN-div compared to the state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:1712.01026

Code (1)

Lornatang/WassersteinGAN_DIV-PyTorch pytorch

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Bridging the Gap Between $f$-GANs and Wasserstein GANs

2019-10-22 · Jiaming Song, Stefano Ermon

Generative adversarial networks (GANs) have enjoyed much success in learning high-dimensional distributions. Learning objectives approximately minimize an $f$-divergence ($f$-GANs) or an integral probability metric (Wass…

Image Generation

On Relativistic f-Divergences

2020-01-01 · ICML 2020 1 · Alexia Jolicoeur-Martineau

We take a more rigorous look at Relativistic Generative Adversarial Networks (RGANs) and prove that the objective function of the discriminator is a statistical divergence for any concave function $f$ with minimal proper…

On Relativistic $f$-Divergences

2019-01-08 · Alexia Jolicoeur-Martineau

This paper provides a more rigorous look at Relativistic Generative Adversarial Networks (RGANs). We prove that the objective function of the discriminator is a statistical divergence for any concave function $f$ with mi…

Approximability of Discriminators Implies Diversity in GANs

2018-06-27 · ICLR 2019 5 · Yu Bai, Tengyu Ma, Andrej Risteski

While Generative Adversarial Networks (GANs) have empirically produced impressive results on learning complex real-world distributions, recent works have shown that they suffer from lack of diversity or mode collapse. Th…

Diversity

Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator

2020-04-05 · Yuxuan Song, Qiwei Ye, Minkai Xu, Tie-Yan Liu

Generative Adversarial Networks (GANs) have shown great promise in modeling high dimensional data. The learning objective of GANs usually minimizes some measure discrepancy, \textit{e.g.}, $f$-divergence~($f$-GANs) or In…

Image Generation