Multi-Adversarial Variational Autoencoder Networks
This work addresses image generation and classification tasks in computer vision and medical imaging, presenting an incremental improvement by integrating existing generative models with a multi-adversarial approach.
The authors tackled the problem of generating realistic synthetic images and performing semi-supervised classification by introducing Multi-Adversarial Variational autoEncoder Networks (MAVENs), which combine VAEs and GANs with an ensemble of discriminators, achieving competitive performance against state-of-the-art models on datasets like SVHN, CIFAR-10, and Chest X-Ray.
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.