Discriminative deep-learning models are often reliant on copious labeled training data. By contrast, from relatively small corpora of training data, deep generative models can learn to generate realistic images approximating real-world distributions. In particular, the proper training of Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs) enables them to perform semi-supervised image classification. Combining the power of these two models, we introduce Multi-Adversarial Variational autoEncoder Networks (MAVENs), a novel deep generative model that incorporates an ensemble of discriminators in a VAE-GAN network in order to perform 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 these images. Our experimental results with only 10% labeled training data from the computer vision and medical imaging domains demonstrate performance competitive to state-of-the-art semi-supervised models in simultaneous image generation and classification tasks.
|Title of host publication||Advances in Intelligent Systems and Computing|
|Number of pages||23|
|State||Published - 2021|
|Name||Advances in Intelligent Systems and Computing|
Bibliographical notePublisher Copyright:
© 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
ASJC Scopus subject areas
- Control and Systems Engineering
- Computer Science (all)