# Multi-Adversarial Variational Autoencoder Networks

## TL;DR

MAVENs is a novel ensemble discriminator architecture combining VAEs and GANs, enhancing image generation and classification in semi-supervised learning across diverse datasets.

## Contribution

Introduces MAVENs, a new network architecture with multiple discriminators for improved semi-supervised image generation and classification.

## Key findings

- Competitive performance on CIFAR-10, SVHN, and Chest X-Ray datasets.
- Effective in both image synthesis and semi-supervised classification.
- Outperforms some state-of-the-art models in experiments.

## Abstract

The unsupervised training of GANs and VAEs has enabled them to generate realistic images mimicking real-world distributions and perform image-based unsupervised clustering or semi-supervised classification. Combining the power of these two generative models, we introduce Multi-Adversarial Variational autoEncoder Networks (MAVENs), a novel network architecture that incorporates an ensemble of discriminators in a VAE-GAN network, with simultaneous adversarial learning and variational inference. We apply MAVENs to the generation of synthetic images and propose a new distribution measure to quantify the quality of the generated images. Our experimental results using datasets from the computer vision and medical imaging domains---Street View House Numbers, CIFAR-10, and Chest X-Ray datasets---demonstrate competitive performance against state-of-the-art semi-supervised models both in image generation and classification tasks.