Mixture variational autoencoders

doi:10.1016/j.patrec.2019.09.007

Mixture variational autoencoders

2019-12-01

5

PRE

AI

DOI：10.1016/j.patrec.2019.09.007

Original

Original request for help

Save

Abstract

En 中文

Variational autoencoders (VAEs) combine a generative model and a recognition model, and jointly train them to maximize a variational lower bound. VAEs play an important role in unsupervised learning and representation learning. But the isotropic generative model in VAEs cannot sufficiently utilize the latent representative space. In this paper, we present mixture variational autoencoders (MVAEs) which suppose observed data is generated from mixture models. We use a continuous variable with prior of Normal distribution as the latent representation, and introduce a discrete variable with prior of Multinomial distribution as latent indicator for mixture models. Two latent variables are both approximated by recognition models computed from neural networks. Furthermore, we combine the reparameterization trick and stick-breaking parameterization to realize stochastic gradient variational Bayes (SGVB) estimator on our variational objective. The MVAEs improve the generative performance by enlarging the latent representative space. Finally, we demonstrate the performance of MVAEs compared with the state-of-the-art models on MNIST, OMNIGLOT, and Fashion-MNIST. (C) 2019 Elsevier B.V. All rights reserved.

Keywords:

Mixture variational autoencoders

Mixture models

Reparameterization trick

SGVB estimator

Mixture variational autoencoders

Abstract

AI Summary

Journal

Organization