UaiNets: From Unsupervised to Active Deep Anomaly Detection

Abstract

This work presents a method for active anomaly detection which can be built upon existing deep learning solutions for unsupervised anomaly detection. We show that a prior needs to be assumed on what the anomalies are, in order to have performance guarantees in unsupervised anomaly detection. We argue that active anomaly detection has, in practice, the same cost of unsupervised anomaly detection but with the possibility of much better results. To solve this problem, we present a new layer that can be attached to any deep learning model designed for unsupervised anomaly detection to transform it into an active method, presenting results on both synthetic and real anomaly detection datasets.

Tasks

Reproductions