One-Class Slab Support Vector Machine

TL;DR

This paper introduces the one-class slab SVM (OCSSVM), a novel classifier that improves detection accuracy of novel class instances by using two parallel hyperplanes, extending one-class SVM with scalable non-linear decision functions.

Contribution

The paper proposes OCSSVM, a new one-class classifier that reduces false positives and enhances detection of novel class instances using a hyperplane-based approach.

Findings

OCSSVM outperforms traditional one-class SVM in experiments.

OCSSVM achieves comparable or better results than state-of-the-art classifiers.

The method scales well and learns non-linear decision functions.

Abstract

This work introduces the one-class slab SVM (OCSSVM), a one-class classifier that aims at improving the performance of the one-class SVM. The proposed strategy reduces the false positive rate and increases the accuracy of detecting instances from novel classes. To this end, it uses two parallel hyperplanes to learn the normal region of the decision scores of the target class. OCSSVM extends one-class SVM since it can scale and learn non-linear decision functions via kernel methods. The experiments on two publicly available datasets show that OCSSVM can consistently outperform the one-class SVM and perform comparable to or better than other state-of-the-art one-class classifiers.