Corpus ID: 208513049

Orthogonal Wasserstein GANs

@article{Mller2019OrthogonalWG,
  title={Orthogonal Wasserstein GANs},
  author={Jan Steffen M{\"u}ller and R. Klein and Michael Weinmann},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.13060}
}
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 convergence behaviour and improved image quality. However, Wasserstein-GANs require the discriminator to be Lipschitz continuous. In current state-of-the-art Wasserstein-GANs this constraint is enforced via gradient norm regularization. In this paper, we demonstrate that this… Expand
Normalization Techniques in Training DNNs: Methodology, Analysis and Application
TLDR
A unified picture of the main motivation behind different approaches from the perspective of optimization is provided, and a taxonomy for understanding the similarities and differences between them is presented. Expand

References

SHOWING 1-10 OF 39 REFERENCES
Improved Training of Wasserstein GANs
TLDR
This work proposes an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input, which performs better than standard WGAN and enables stable training of a wide variety of GAN architectures with almost no hyperparameter tuning. Expand
VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
TLDR
VEEGAN is introduced, which features a reconstructor network, reversing the action of the generator by mapping from data to noise, and resists mode collapsing to a far greater extent than other recent GAN variants, and produces more realistic samples. Expand
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
TLDR
This work proposes a two time-scale update rule (TTUR) for training GANs with stochastic gradient descent on arbitrary GAN loss functions and introduces the "Frechet Inception Distance" (FID) which captures the similarity of generated images to real ones better than the Inception Score. Expand
Banach Wasserstein GAN
TLDR
The theory of WGAN with gradient penalty to Banach spaces is generalized, allowing practitioners to select the features to emphasize in the generator. Expand
Improved Techniques for Training GANs
TLDR
This work focuses on two applications of GANs: semi-supervised learning, and the generation of images that humans find visually realistic, and presents ImageNet samples with unprecedented resolution and shows that the methods enable the model to learn recognizable features of ImageNet classes. Expand
A Classification-Based Study of Covariate Shift in GAN Distributions
A basic, and still largely unanswered, question in the context of Generative Adversarial Networks (GANs) is whether they are truly able to capture all the fundamental characteristics of theExpand
Large Scale GAN Training for High Fidelity Natural Image Synthesis
TLDR
It is found that applying orthogonal regularization to the generator renders it amenable to a simple "truncation trick," allowing fine control over the trade-off between sample fidelity and variety by reducing the variance of the Generator's input. Expand
Progressive Growing of GANs for Improved Quality, Stability, and Variation
TLDR
A new training methodology for generative adversarial networks is described, starting from a low resolution, and adding new layers that model increasingly fine details as training progresses, allowing for images of unprecedented quality. Expand
Sorting out Lipschitz function approximation
TLDR
This work identifies a necessary property for such an architecture: each of the layers must preserve the gradient norm during backpropagation, and proposes to combine a gradient norm preserving activation function, GroupSort, with norm-constrained weight matrices that are universal Lipschitz function approximators. Expand
Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?
TLDR
This paper develops novel orthogonality regularizations on training deep CNNs, utilizing various advanced analytical tools such as mutual coherence and restricted isometry property to develop plug-and-play regularizations that can be conveniently incorporated into training almost any CNN without extra hassle. Expand
...
1
2
3
4
...