Prb-GAN: A Probabilistic Framework for GAN Modelling

07/12/2021
by   Blessen George, et al.
0

Generative adversarial networks (GANs) are very popular to generate realistic images, but they often suffer from the training instability issues and the phenomenon of mode loss. In order to attain greater diversity in GAN synthesized data, it is critical to solving the problem of mode loss. Our work explores probabilistic approaches to GAN modelling that could allow us to tackle these issues. We present Prb-GANs, a new variation that uses dropout to create a distribution over the network parameters with the posterior learnt using variational inference. We describe theoretically and validate experimentally using simple and complex datasets the benefits of such an approach. We look into further improvements using the concept of uncertainty measures. Through a set of further modifications to the loss functions for each network of the GAN, we are able to get results that show the improvement of GAN performance. Our methods are extremely simple and require very little modification to existing GAN architecture.

READ FULL TEXT

page 6

page 7

research
06/25/2021

Fostering Diversity in Spatial Evolutionary Generative Adversarial Networks

Generative adversary networks (GANs) suffer from training pathologies su...
research
04/22/2020

Stabilizing Training of Generative Adversarial Nets via Langevin Stein Variational Gradient Descent

Generative adversarial networks (GANs), famous for the capability of lea...
research
11/23/2018

Do GAN Loss Functions Really Matter?

In this paper, we address the recent controversy between Lipschitz regul...
research
06/25/2020

Empirical Analysis of Overfitting and Mode Drop in GAN Training

We examine two key questions in GAN training, namely overfitting and mod...
research
02/14/2020

Top-K Training of GANs: Improving Generators by Making Critics Less Critical

We introduce a simple (one line of code) modification to the Generative ...
research
07/25/2018

How good is my GAN?

Generative adversarial networks (GANs) are one of the most popular metho...
research
08/25/2022

Adversarial Bayesian Simulation

In the absence of explicit or tractable likelihoods, Bayesians often res...

Please sign up or login with your details

Forgot password? Click here to reset