PBES: PCA Based Exemplar Sampling Algorithm for Continual Learning

TL;DR

This paper introduces a PCA-based exemplar sampling method for continual learning that improves performance by effectively selecting representative data points and avoiding outliers, applicable across various models.

Contribution

It presents a novel PCA and median sampling approach for exemplar selection in class-incremental learning, enhancing performance and simplicity over existing methods.

Findings

Outperforms state-of-the-art exemplar selection methods.

Effectively handles outliers in data sampling.

Applicable across different incremental learning models.

Abstract

We propose a novel exemplar selection approach based on Principal Component Analysis (PCA) and median sampling, and a neural network training regime in the setting of class-incremental learning. This approach avoids the pitfalls due to outliers in the data and is both simple to implement and use across various incremental machine learning models. It also has independent usage as a sampling algorithm. We achieve better performance compared to state-of-the-art methods.