Bayesian Generative Active Deep Learning

TL;DR

This paper introduces a Bayesian generative active deep learning method that combines active learning and data augmentation, leading to more efficient training and improved classification performance on benchmark datasets.

Contribution

It proposes a novel Bayesian generative approach that integrates active learning with data augmentation, enhancing training efficiency and accuracy.

Findings

More efficient training compared to existing methods

Better classification results on benchmark datasets

Empirical validation on MNIST, CIFAR-10/100, SVHN

Abstract

Deep learning models have demonstrated outstanding performance in several problems, but their training process tends to require immense amounts of computational and human resources for training and labeling, constraining the types of problems that can be tackled. Therefore, the design of effective training methods that require small labeled training sets is an important research direction that will allow a more effective use of resources.Among current approaches designed to address this issue, two are particularly interesting: data augmentation and active learning. Data augmentation achieves this goal by artificially generating new training points, while active learning relies on the selection of the "most informative" subset of unlabeled training samples to be labelled by an oracle. Although successful in practice, data augmentation can waste computational resources because it indiscriminately generates samples that are not guaranteed to be informative, and active learning selects a small subset of informative samples (from a large un-annotated set) that may be insufficient for the training process. In this paper, we propose a Bayesian generative active deep learning approach that combines active learning with data augmentation -- we provide theoretical and empirical evidence (MNIST, CIFAR-$\{10,100\}$, and SVHN) that our approach has more efficient training and better classification results than data augmentation and active learning.