Continual Learning Approaches for Anomaly Detection

TL;DR

This paper introduces SCALE, a novel image compression and reconstruction method using Super Resolution for continual learning-based anomaly detection, demonstrating high compression efficiency and effective anomaly detection on real-world datasets.

Contribution

The paper presents SCALE, a new approach combining image scaling and compression with Super Resolution for continual learning anomaly detection, a novel application in this context.

Findings

High compression ratios with quality preservation

Effective anomaly detection performance

Provides a new benchmark dataset for the field

Abstract

Anomaly Detection is a relevant problem that arises in numerous real-world applications, especially when dealing with images. However, there has been little research for this task in the Continual Learning setting. In this work, we introduce a novel approach called SCALE (SCALing is Enough) to perform Compressed Replay in a framework for Anomaly Detection in Continual Learning setting. The proposed technique scales and compresses the original images using a Super Resolution model which, to the best of our knowledge, is studied for the first time in the Continual Learning setting. SCALE can achieve a high level of compression while maintaining a high level of image reconstruction quality. In conjunction with other Anomaly Detection approaches, it can achieve optimal results. To validate the proposed approach, we use a real-world dataset of images with pixel-based anomalies, with the scope to provide a reliable benchmark for Anomaly Detection in the context of Continual Learning, serving as a foundation for further advancements in the field.