A Class-Incremental Learning Method Based on One Class Support Vector Machine

TL;DR

This paper introduces a class-incremental learning approach utilizing one class support vector machines (OCSVMs) that efficiently updates models by reusing support vectors, reducing memory and training costs.

Contribution

It proposes a novel class-incremental learning method based on OCSVMs that retains original models and improves efficiency over traditional approaches.

Findings

Reduces memory consumption compared to traditional methods.

Decreases training time by reusing support vectors.

Proves effective across various datasets.

Abstract

A method based on one class support vector machine (OCSVM) is proposed for class incremental learning. Several OCSVM models divide the input space into several parts. Then, the 1VS1 classifiers are constructed for the confuse part by using the support vectors. During the class incremental learning process, the OCSVM of the new class is trained at first. Then the support vectors of the old classes and the support vectors of the new class are reused to train 1VS1 classifiers for the confuse part. In order to bring more information to the certain support vectors, the support vectors are at the boundary of the distribution of samples as much as possible when the OCSVM is built. Compared with the traditional methods, the proposed method retains the original model and thus reduces memory consumption and training time cost. Various experiments on different datasets also verify the efficiency of the proposed method.