Multi-Class Anomaly Detection
This work addresses anomaly detection for scenarios with multiple normal categories, which is an incremental improvement over standard one-class methods.
The paper tackles the problem of multi-class anomaly detection, where the normal class includes multiple object categories, and shows that training a single one-class anomaly detector on all normal categories outperforms using multiple one-class detectors. The proposed DeepMAD algorithm achieves higher AUC values on datasets like CIFAR-10, fMNIST, CIFAR-100, and RECYCLE compared to existing methods.
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.