Active Learning for Convolutional Neural Networks: A Core-Set Approach

TL;DR

This paper introduces a core-set based active learning method for CNNs that effectively selects informative samples, reducing labeling costs while maintaining high classification performance, and outperforms existing methods significantly.

Contribution

It formulates active learning as core-set selection for CNNs, providing a theoretical framework and a practical algorithm that outperforms previous heuristics.

Findings

Proposed method outperforms existing active learning heuristics in image classification.

Theoretical analysis links core-set selection to data geometry and model performance.

Empirical results demonstrate large margin improvements in labeling efficiency.

Abstract

Convolutional neural networks (CNNs) have been successfully applied to many recognition and learning tasks using a universal recipe; training a deep model on a very large dataset of supervised examples. However, this approach is rather restrictive in practice since collecting a large set of labeled images is very expensive. One way to ease this problem is coming up with smart ways for choosing images to be labelled from a very large collection (ie. active learning). Our empirical study suggests that many of the active learning heuristics in the literature are not effective when applied to CNNs in batch setting. Inspired by these limitations, we define the problem of active learning as core-set selection, ie. choosing set of points such that a model learned over the selected subset is competitive for the remaining data points. We further present a theoretical result characterizing the performance of any selected subset using the geometry of the datapoints. As an active learning algorithm, we choose the subset which is expected to yield best result according to our characterization. Our experiments show that the proposed method significantly outperforms existing approaches in image classification experiments by a large margin.