Implicit Discriminator in Variational Autoencoder

TL;DR

The paper introduces IDVAE, a hybrid VAE-GAN architecture that shares components to improve generative quality without needing an explicit discriminator, outperforming existing hybrid models.

Contribution

IDVAE is a novel hybrid architecture that combines VAE and GAN components into a shared network, eliminating the need for an explicit discriminator.

Findings

IDVAE outperforms state-of-the-art hybrid models on benchmark datasets.

IDVAE can be extended to conditional generation tasks.

IDVAE demonstrates strong performance on complex datasets.

Abstract

Recently generative models have focused on combining the advantages of variational autoencoders (VAE) and generative adversarial networks (GAN) for good reconstruction and generative abilities. In this work we introduce a novel hybrid architecture, Implicit Discriminator in Variational Autoencoder (IDVAE), that combines a VAE and a GAN, which does not need an explicit discriminator network. The fundamental premise of the IDVAE architecture is that the encoder of a VAE and the discriminator of a GAN utilize common features and therefore can be trained as a shared network, while the decoder of the VAE and the generator of the GAN can be combined to learn a single network. This results in a simple two-tier architecture that has the properties of both a VAE and a GAN. The qualitative and quantitative experiments on real-world benchmark datasets demonstrates that IDVAE perform better than the state of the art hybrid approaches. We experimentally validate that IDVAE can be easily extended to work in a conditional setting and demonstrate its performance on complex datasets.