One-Class Slab Support Vector Machine
This work addresses the need for more accurate one-class classifiers in anomaly or novelty detection tasks, though it appears incremental as it builds upon existing one-class SVM methods.
The paper tackles the problem of improving one-class classification by introducing the one-class slab SVM (OCSSVM), which reduces false positives and increases accuracy in detecting novel class instances, showing consistent outperformance over one-class SVM and competitive results with other state-of-the-art methods on two datasets.
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.