Shared Loss between Generators of GANs

TL;DR

This paper introduces a novel GAN training approach where multiple generators compete against each other while interacting with a discriminator, significantly reducing training time without sacrificing output quality.

Contribution

It proposes a new shared loss mechanism among multiple generators in GANs, promoting competition and interaction to improve training efficiency.

Findings

Training time is significantly reduced.

Mode collapse is mitigated.

Output quality remains high.

Abstract

Generative adversarial networks are generative models that are capable of replicating the implicit probability distribution of the input data with high accuracy. Traditionally, GANs consist of a Generator and a Discriminator which interact with each other to produce highly realistic artificial data. Traditional GANs fall prey to the mode collapse problem, which means that they are unable to generate the different variations of data present in the input dataset. Recently, multiple generators have been used to produce more realistic output by mitigating the mode collapse problem. We use this multiple generator framework. The novelty in this paper lies in making the generators compete against each other while interacting with the discriminator simultaneously. We show that this causes a dramatic reduction in the training time for GANs without affecting its performance.