On The Relationship between Visual Anomaly-free and Anomalous Representations

TL;DR

This paper hypothesizes and demonstrates that the space of normal visual patterns correlates with anomalous patterns, potentially improving transfer learning and domain adaptation for anomaly detection in computer vision.

Contribution

It introduces a novel hypothesis linking anomaly-free and anomalous representations, supported by exhaustive experiments, to enhance transfer learning for anomaly detection.

Findings

Normal and anomalous visual pattern spaces are correlated.

Transfer learning from normal to anomalous domains shows promising results.

Potential for improved domain adaptation and few-shot anomaly detection.

Abstract

Anomaly Detection is an important problem within computer vision, having variety of real-life applications. Yet, the current set of solutions to this problem entail known, systematic shortcomings. Specifically, contemporary surface Anomaly Detection task assumes the presence of multiple specific anomaly classes e.g. cracks, rusting etc., unlike one-class classification model of past. However, building a deep learning model in such setup remains a challenge because anomalies arise rarely, and hence anomaly samples are quite scarce. Transfer learning has been a preferred paradigm in such situations. But the typical source domains with large dataset sizes e.g. ImageNet, JFT-300M, LAION-2B do not correlate well with the domain of surfaces and materials, an important premise of transfer learning. In this paper, we make an important hypothesis and show, by exhaustive experimentation, that the space of anomaly-free visual patterns of the normal samples correlates well with each of the various spaces of anomalous patterns of the class-specific anomaly samples. The first results of using this hypothesis in transfer learning have indeed been quite encouraging. We expect that finding such a simple closeby domain that readily entails large number of samples, and which also oftentimes shows interclass separability though with narrow margins, will be a useful discovery. Especially, it is expected to improve domain adaptation for anomaly detection, and few-shot learning for anomaly detection, making in-the-wild anomaly detection realistically possible in future.