Prb-GAN: A Probabilistic Framework for GAN Modelling

TL;DR

Prb-GAN introduces a probabilistic approach using dropout and variational inference to improve GAN training stability and diversity, effectively addressing mode loss with minimal architectural changes.

Contribution

It proposes a novel probabilistic GAN framework, Prb-GAN, that enhances diversity and stability by modeling network parameters probabilistically with dropout and variational inference.

Findings

Improved diversity in generated images.

Enhanced training stability.

Minimal modifications needed for existing GANs.

Abstract

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.