A Study into the similarity in generator and discriminator in GAN architecture

TL;DR

This paper investigates the structural similarities between generator and discriminator networks in GANs, providing experimental evidence that they can share architecture, which could influence future design choices.

Contribution

It presents a novel shared architecture for GAN components and demonstrates their structural similarity through experimental analysis.

Findings

Generator and discriminator can have similar structures

Shared architecture improves understanding of GAN components

Experimental results support the feasibility of shared networks

Abstract

One popular generative model that has high-quality results is the Generative Adversarial Networks(GAN). This type of architecture consists of two separate networks that play against each other. The generator creates an output from the input noise that is given to it. The discriminator has the task of determining if the input to it is real or fake. This takes place constantly eventually leads to the generator modeling the target distribution. This paper includes a study into the actual weights learned by the network and a study into the similarity of the discriminator and generator networks. The paper also tries to leverage the similarity between these networks and shows that indeed both the networks may have a similar structure with experimental evidence with a novel shared architecture.