Variational Autoencoder for Deep Learning of Images, Labels and Captions

TL;DR

This paper introduces a variational autoencoder framework that jointly models images, labels, and captions, enabling semi-supervised and unsupervised learning with efficient inference.

Contribution

It combines a deep generative deconvolutional network with a CNN encoder and integrates label and caption modeling, advancing semi-supervised and unsupervised image learning.

Findings

Efficient averaging over latent codes improves prediction.

Framework supports semi-supervised learning with labels.

Allows unsupervised CNN training on images alone.

Abstract

A novel variational autoencoder is developed to model images, as well as associated labels or captions. The Deep Generative Deconvolutional Network (DGDN) is used as a decoder of the latent image features, and a deep Convolutional Neural Network (CNN) is used as an image encoder; the CNN is used to approximate a distribution for the latent DGDN features/code. The latent code is also linked to generative models for labels (Bayesian support vector machine) or captions (recurrent neural network). When predicting a label/caption for a new image at test, averaging is performed across the distribution of latent codes; this is computationally efficient as a consequence of the learned CNN-based encoder. Since the framework is capable of modeling the image in the presence/absence of associated labels/captions, a new semi-supervised setting is manifested for CNN learning with images; the framework even allows unsupervised CNN learning, based on images alone.