Image anomaly detection with capsule networks and imbalanced datasets

TL;DR

This paper introduces a novel image anomaly detection system utilizing capsule networks, designed to work effectively with scarce anomalous training data, addressing limitations of traditional methods.

Contribution

The paper presents a new deep learning approach using capsule networks for anomaly detection with imbalanced datasets, filling a gap in current research.

Findings

Capsule networks improve anomaly detection accuracy.

The method performs well with limited anomalous data.

Compared to traditional methods, it offers enhanced detection capabilities.

Abstract

Image anomaly detection consists in finding images with anomalous, unusual patterns with respect to a set of normal data. Anomaly detection can be applied to several fields and has numerous practical applications, e.g. in industrial inspection, medical imaging, security enforcement, etc.. However, anomaly detection techniques often still rely on traditional approaches such as one-class Support Vector Machines, while the topic has not been fully developed yet in the context of modern deep learning approaches. In this paper, we propose an image anomaly detection system based on capsule networks under the assumption that anomalous data are available for training but their amount is scarce.