SupportNet: solving catastrophic forgetting in class incremental learning with support data

TL;DR

SupportNet is a novel approach that combines deep learning with support vector machines to mitigate catastrophic forgetting in class incremental learning, maintaining high performance on old and new data.

Contribution

It introduces a support data selection method and regularizers to stabilize learning, significantly improving incremental learning performance over existing methods.

Findings

SupportNet outperforms state-of-the-art incremental learning methods.

SupportNet achieves performance comparable to training from scratch.

SupportNet effectively preserves old knowledge while learning new classes.

Abstract

A plain well-trained deep learning model often does not have the ability to learn new knowledge without forgetting the previously learned knowledge, which is known as catastrophic forgetting. Here we propose a novel method, SupportNet, to efficiently and effectively solve the catastrophic forgetting problem in the class incremental learning scenario. SupportNet combines the strength of deep learning and support vector machine (SVM), where SVM is used to identify the support data from the old data, which are fed to the deep learning model together with the new data for further training so that the model can review the essential information of the old data when learning the new information. Two powerful consolidation regularizers are applied to stabilize the learned representation and ensure the robustness of the learned model. We validate our method with comprehensive experiments on various tasks, which show that SupportNet drastically outperforms the state-of-the-art incremental learning methods and even reaches similar performance as the deep learning model trained from scratch on both old and new data. Our program is accessible at: https://github.com/lykaust15/SupportNet