Multi-Class Anomaly Detection

TL;DR

This paper introduces DeepMAD, a novel multi-class anomaly detection algorithm that outperforms traditional methods by learning compact features across multiple normal object categories, validated on several datasets.

Contribution

The paper proposes DeepMAD, a new anomaly detector that effectively handles multiple normal classes, improving detection performance over existing one-class methods.

Findings

DeepMAD achieves higher AUC scores on multiple datasets.

Joint training of multiple one-class detectors performs worse than a single combined detector.

Empirical validation on CIFAR-10, fMNIST, CIFAR-100, and RECYCLE datasets.

Abstract

We study anomaly detection for the case when the normal class consists of more than one object category. This is an obvious generalization of the standard one-class anomaly detection problem. However, we show that jointly using multiple one-class anomaly detectors to solve this problem yields poorer results as compared to training a single one-class anomaly detector on all normal object categories together. We further develop a new anomaly detector called DeepMAD that learns compact distinguishing features by exploiting the multiple normal objects categories. This algorithm achieves higher AUC values for different datasets compared to two top performing one-class algorithms that either are trained on each normal object category or jointly trained on all normal object categories combined. In addition to theoretical results we present empirical results using the CIFAR-10, fMNIST, CIFAR-100, and a new dataset we developed called RECYCLE.