Using Sum-Product Networks to Assess Uncertainty in Deep Active Learning

TL;DR

This paper introduces a simple method for uncertainty estimation in deep active learning by training Sum-Product Networks on CNN feature representations, improving data point ranking for labeling.

Contribution

It proposes using Sum-Product Networks on CNN features to estimate uncertainty, offering a straightforward approach that enhances active learning strategies.

Findings

Outperforms existing uncertainty estimation methods on benchmark datasets.

Effective in improving the selection of informative data points.

Compatible with standard acquisition functions like max entropy.

Abstract

The success of deep active learning hinges on the choice of an effective acquisition function, which ranks not yet labeled data points according to their expected informativeness. Many acquisition functions are (partly) based on the uncertainty that the current model has about the class label of a point, yet there is no generally agreed upon strategy for computing such uncertainty. This paper proposes a new and very simple approach to computing uncertainty in deep active learning with a Convolutional Neural Network (CNN). The main idea is to use the feature representation extracted by the CNN as data for training a Sum-Product Network (SPN). Since SPNs are typically used for estimating the distribution of a dataset, they are well suited to the task of estimating class probabilities that can be used directly by standard acquisition functions such as max entropy and variational ratio. The effectiveness of our method is demonstrated in an experimental study on several standard benchmark datasets for image classification, where we compare it to various state-of-the-art methods for assessing uncertainty in deep active learning.