Maximally Separated Active Learning

TL;DR

This paper introduces MSAL, a novel active learning approach that uses equiangular hyperspherical points to ensure maximal class separation, improving sample selection efficiency without clustering.

Contribution

The paper proposes a new active learning method utilizing fixed hyperspherical class prototypes to enhance diversity and separation, eliminating clustering steps.

Findings

Outperforms existing active learning methods on five benchmark datasets.

Ensures robust feature representations through hyperspherical uniformity.

Simplifies active learning by removing clustering requirements.

Abstract

Active Learning aims to optimize performance while minimizing annotation costs by selecting the most informative samples from an unlabelled pool. Traditional uncertainty sampling often leads to sampling bias by choosing similar uncertain samples. We propose an active learning method that utilizes fixed equiangular hyperspherical points as class prototypes, ensuring consistent inter-class separation and robust feature representations. Our approach introduces Maximally Separated Active Learning (MSAL) for uncertainty sampling and a combined strategy (MSAL-D) for incorporating diversity. This method eliminates the need for costly clustering steps, while maintaining diversity through hyperspherical uniformity. We demonstrate strong performance over existing active learning techniques across five benchmark datasets, highlighting the method's effectiveness and integration ease. The code is available on GitHub.