Multi-adversarial Variational Autoencoder Networks

The unsupervised training of GANs and VAEs has enabled them to generate realistic images mimicking real-world distributions and perform unsupervised clustering or semi-supervised classification of images. Combining the power of these two generative models, we introduce a novel network architecture,...

Full description

Saved in:

Bibliographic Details
Published in:	2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA) pp. 777 - 782
Main Authors:	Imran, Abdullah-Al-Zubaer, Terzopoulos, Demetri
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.12.2019
Subjects:	Computational modeling Data models Deep-generative-models Gallium nitride GANs Generators Image generation image-classification semi-supervised-learning Supervised learning Training VAEs
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	The unsupervised training of GANs and VAEs has enabled them to generate realistic images mimicking real-world distributions and perform unsupervised clustering or semi-supervised classification of images. Combining the power of these two generative models, we introduce a novel network architecture, Multi-Adversarial Variational autoEncoder Networks (MAVENs), which incorporate an ensemble of discriminators in a combined 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 evaluate the quality of the generated images. Our experimental results using the computer vision datasets SVHN and CIFAR-10 demonstrate competitive performance against state-of-the-art semi-supervised models both in image generation and classification tasks.
DOI:	10.1109/ICMLA.2019.00137