Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference

TL;DR

This paper introduces a Bayesian CNN model using Bernoulli variational inference that enhances robustness against overfitting on small datasets, improves classification accuracy, and can be implemented efficiently with existing deep learning tools.

Contribution

It presents a novel Bayesian CNN approach with Bernoulli variational distributions, unifying dropout training with Bayesian inference, and demonstrates improved performance on small datasets.

Findings

Better robustness to overfitting on small data

Improved classification accuracy on CIFAR-10

Dropout training as approximate Bayesian inference

Abstract

Convolutional neural networks (CNNs) work well on large datasets. But labelled data is hard to collect, and in some applications larger amounts of data are not available. The problem then is how to use CNNs with small data -- as CNNs overfit quickly. We present an efficient Bayesian CNN, offering better robustness to over-fitting on small data than traditional approaches. This is by placing a probability distribution over the CNN's kernels. We approximate our model's intractable posterior with Bernoulli variational distributions, requiring no additional model parameters. On the theoretical side, we cast dropout network training as approximate inference in Bayesian neural networks. This allows us to implement our model using existing tools in deep learning with no increase in time complexity, while highlighting a negative result in the field. We show a considerable improvement in classification accuracy compared to standard techniques and improve on published state-of-the-art results for CIFAR-10.