VARGAN: Variance Enforcing Network Enhanced GAN

TL;DR

VARGAN introduces a third network to enforce diversity in GAN outputs, improving sample variety, reducing mode collapse, and achieving faster convergence with low computational cost.

Contribution

The paper proposes VARGAN, a novel GAN architecture with a third network that penalizes low-diversity samples, enhancing diversity and training stability.

Findings

VARGAN produces more diverse samples than state-of-the-art models.

VARGAN demonstrates fast convergence and low computational complexity.

VARGAN effectively alleviates mode collapse in GAN training.

Abstract

Generative adversarial networks (GANs) are one of the most widely used generative models. GANs can learn complex multi-modal distributions, and generate real-like samples. Despite the major success of GANs in generating synthetic data, they might suffer from unstable training process, and mode collapse. In this paper, we introduce a new GAN architecture called variance enforcing GAN (VARGAN), which incorporates a third network to introduce diversity in the generated samples. The third network measures the diversity of the generated samples, which is used to penalize the generator's loss for low diversity samples. The network is trained on the available training data and undesired distributions with limited modality. On a set of synthetic and real-world image data, VARGAN generates a more diverse set of samples compared to the recent state-of-the-art models. High diversity and low computational complexity, as well as fast convergence, make VARGAN a promising model to alleviate mode collapse.