Multi-Scale Memory Comparison for Zero-/Few-Shot Anomaly Detection

TL;DR

This paper introduces a multi-scale memory comparison framework for zero-/few-shot anomaly detection in industrial scenarios, effectively handling multiple objects and achieving top competition results.

Contribution

It proposes a novel multi-scale memory comparison approach combining global and object-focused memory banks for improved anomaly detection with minimal data.

Findings

Achieved 4th place in zero-shot track of VAND competition.

Secured 2nd place in few-shot track of VAND competition.

Demonstrated effectiveness in complex industrial defect detection scenarios.

Abstract

Anomaly detection has gained considerable attention due to its broad range of applications, particularly in industrial defect detection. To address the challenges of data collection, researchers have introduced zero-/few-shot anomaly detection techniques that require minimal normal images for each category. However, complex industrial scenarios often involve multiple objects, presenting a significant challenge. In light of this, we propose a straightforward yet powerful multi-scale memory comparison framework for zero-/few-shot anomaly detection. Our approach employs a global memory bank to capture features across the entire image, while an individual memory bank focuses on simplified scenes containing a single object. The efficacy of our method is validated by its remarkable achievement of 4th place in the zero-shot track and 2nd place in the few-shot track of the Visual Anomaly and Novelty Detection (VAND) competition.