Variational Autoencoders with Normalizing Flow Decoders

Rogan Morrow, Wei-Chen Chiu

Abstract: Recently proposed normalizing flow models such as Glow (Kingma & Dhariwal, 2018) have been shown to be able to generate high quality, high dimensional images with relatively fast sampling speed. Due to the inherently restrictive design of architecture , however, it is necessary that their model are excessively deep in order to achieve effective training. In this paper we propose to combine Glow model with an underlying variational autoencoder in order to counteract this issue. We demonstrate that such our proposed model is competitive with Glow in terms of image quality while requiring far less time for training. Additionally, our model achieves state-of-the-art FID score on CIFAR-10 for a likelihood-based model.