Deep Bayesian Active Semi-Supervised Learning

TL;DR

This paper introduces a novel deep learning method that combines active and semi-supervised learning to achieve high accuracy with minimal labeled data, reducing labeling effort while maintaining performance.

Contribution

The paper presents a new approach integrating active learning with semi-supervised deep neural networks, improving label efficiency without specialized architectures.

Findings

Achieved 2.06% error on MNIST with 300 labels

Achieved 1.06% error on MNIST with 1000 labels

Method does not rely on special architectures or data augmentation

Abstract

In many applications the process of generating label information is expensive and time consuming. We present a new method that combines active and semi-supervised deep learning to achieve high generalization performance from a deep convolutional neural network with as few known labels as possible. In a setting where a small amount of labeled data as well as a large amount of unlabeled data is available, our method first learns the labeled data set. This initialization is followed by an expectation maximization algorithm, where further training reduces classification entropy on the unlabeled data by targeting a low entropy fit which is consistent with the labeled data. In addition the algorithm asks at a specified frequency an oracle for labels of data with entropy above a certain entropy quantile. Using this active learning component we obtain an agile labeling process that achieves high accuracy, but requires only a small amount of known labels. For the MNIST dataset we report an error rate of 2.06% using only 300 labels and 1.06% for 1000 labels. These results are obtained without employing any special network architecture or data augmentation.