Anomaly detection in multifactor data

Abstract

In anomaly detection applications, anomalies might come from multiple sources and there might be many reasons why a sample is considered to be anomalous. However, most novel anomaly detection methods do not consider this. In our work, we describe a novel approach that is demonstrated on the problem of detection of anomalies in image data. We propose the SGVAEGAN model, which decomposes the image into three independent components—the shape of an object and its foreground and background textures—and provides anomaly scores for each of those factors separately. The overall anomaly score of an image is a weighted combination of the individual factor scores. The anomaly scores are learned in an unsupervised manner, and the weights are considered as hyperparameters that can be learned in the validation stage. The approach allows the identification of the source of the anomaly using factor scores, as well as the detection of semantic anomalies where the semantic meaning is encoded in the weights and learned from very few samples of validation anomalies. On classical anomaly detection benchmarks, the proposed model outperforms all baseline models. This is shown in a rigorous experimental study that covers the behavior of the model under a varying range of conditions.