Infinite Variational Autoencoder for Semi-Supervised Learning

M. Ehsan Abbasnejad, Anthony Dick, Anton van den Hengel; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 5888-5897

Abstract

This paper presents an infinite variational autoencoder (VAE) whose capacity adapts to suit the input data. This is achieved using a mixture model where the mixing coefficients are modeled by a Dirichlet process, allowing us to integrate over the coefficients when performing inference. Critically, this then allows us to automatically vary the number of autoencoders in the mixture based on the data. Experiments show the flexibility of our method, particularly for semi-supervised learning, where only a small number of training samples are available.

Related Material

[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Abbasnejad_2017_CVPR,
author = {Ehsan Abbasnejad, M. and Dick, Anthony and van den Hengel, Anton},
title = {Infinite Variational Autoencoder for Semi-Supervised Learning},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {July},
year = {2017}
}