Regularized Generative Adversarial Network

TL;DR

This paper introduces RegGAN, a novel framework that employs three networks to generate samples from a different distribution than the training data, with applications in topology and art.

Contribution

The paper presents a new regularized GAN model with three networks, enabling learning of different distributions and topology properties, expanding generative modeling capabilities.

Findings

Successfully generates samples from different distributions.

Learns basic topology properties from data.

Applicable to art-related generative tasks.

Abstract

We propose a framework for generating samples from a probability distribution that differs from the probability distribution of the training set. We use an adversarial process that simultaneously trains three networks, a generator and two discriminators. We refer to this new model as regularized generative adversarial network (RegGAN). We evaluate RegGAN on a synthetic dataset composed of gray scale images and we further show that it can be used to learn some pre-specified notions in topology (basic topology properties). The work is motivated by practical problems encountered while using generative methods in the art world.