PUAD: Frustratingly Simple Method for Robust Anomaly Detection

TL;DR

PUAD introduces a straightforward out-of-distribution detection approach in feature space for logical anomaly detection, outperforming complex reconstruction methods in real-time computer vision tasks.

Contribution

The paper presents PUAD, a simple yet effective out-of-distribution detection method tailored for logical anomalies, challenging the complexity of existing approaches.

Findings

Achieves state-of-the-art performance on MVTec LOCO AD dataset.

Outperforms reconstruction-based anomaly detection methods.

Effective for real-time applications in computer vision.

Abstract

Developing an accurate and fast anomaly detection model is an important task in real-time computer vision applications. There has been much research to develop a single model that detects either structural or logical anomalies, which are inherently distinct. The majority of the existing approaches implicitly assume that the anomaly can be represented by identifying the anomalous location. However, we argue that logical anomalies, such as the wrong number of objects, can not be well-represented by the spatial feature maps and require an alternative approach. In addition, we focused on the possibility of detecting logical anomalies by using an out-of-distribution detection approach on the feature space, which aggregates the spatial information of the feature map. As a demonstration, we propose a method that incorporates a simple out-of-distribution detection method on the feature space against state-of-the-art reconstruction-based approaches. Despite the simplicity of our proposal, our method PUAD (Picturable and Unpicturable Anomaly Detection) achieves state-of-the-art performance on the MVTec LOCO AD dataset.