paper-with-me

홈 › Papers

On the regularization of Wasserstein GANs

2017-09-26 · ICLR 2018 1 · Henning Petzka, Asja Fischer, Denis Lukovnicov

Since their invention, generative adversarial networks (GANs) have become a popular approach for learning to model a distribution of real (unlabeled) data. Convergence problems during training are overcome by Wasserstein GANs which minimize the distance between the model and the empirical distribution in terms of a different metric, but thereby introduce a Lipschitz constraint into the optimization problem. A simple way to enforce the Lipschitz constraint on the class of functions, which can be modeled by the neural network, is weight clipping. It was proposed that training can be improved by instead augmenting the loss by a regularization term that penalizes the deviation of the gradient of the critic (as a function of the network's input) from one. We present theoretical arguments why using a weaker regularization term enforcing the Lipschitz constraint is preferable. These arguments are supported by experimental results on toy data sets.

📄 PDF Abstract BibTeX arXiv:1709.08894

Code (2)

lukovnikov/improved_wgan_training 공식 구현 tf
mikigom/WGAN-LP-tensorflow tf

Similar Papers 제목 키워드 기반

Orthogonal Wasserstein GANs

2019-11-29 · Jan Müller, Reinhard Klein, Michael Weinmann

Wasserstein-GANs have been introduced to address the deficiencies of generative adversarial networks (GANs) regarding the problems of vanishing gradients and mode collapse during the training, leading to improved converg…

Adversarial Lipschitz Regularization

2019-07-12 · ICLR 2020 1 · Dávid Terjék

Generative adversarial networks (GANs) are one of the most popular approaches when it comes to training generative models, among which variants of Wasserstein GANs are considered superior to the standard GAN formulation …

Image Generation

On reproduction of On the regularization of Wasserstein GANs

2017-12-16 · Junghoon Seo, Taegyun Jeon

This report has several purposes. First, our report is written to investigate the reproducibility of the submitted paper On the regularization of Wasserstein GANs (2018). Second, among the experiments performed in the su…

On the estimation of the Wasserstein distance in generative models

2019-10-02 · Thomas Pinetz, Daniel Soukup, Thomas Pock

Generative Adversarial Networks (GANs) have been used to model the underlying probability distribution of sample based datasets. GANs are notoriuos for training difficulties and their dependence on arbitrary hyperparamet…

An Improved Composite Functional Gradient Learning by Wasserstein Regularization for Generative adversarial networks

2021-09-29 · Chang Wan, Yanwei Fu, Ke Fan, Jinshan Zeng 외

Generative adversarial networks (GANs) are usually trained by a minimax game which is notoriously and empirically known to be unstable. Recently, a totally new methodology called Composite Functional Gradient Learning (…

Image Generationregression