Improving Anomaly Detection with Foundation-Model Synthesis and Wavelet-Domain Attention

TL;DR

This paper introduces a novel approach combining foundation-model-based anomaly synthesis and wavelet-domain attention to improve industrial anomaly detection, addressing data scarcity and complex anomaly features.

Contribution

It presents a new anomaly synthesis pipeline (FMAS) and a wavelet domain attention module (WDAM) that enhance detection performance without extensive fine-tuning.

Findings

Significant performance improvements on MVTec AD and VisA datasets.

WDAM effectively exploits frequency-domain features for anomaly detection.

The proposed methods are computationally efficient and easy to integrate.

Abstract

Industrial anomaly detection faces significant challenges due to the scarcity of anomalous samples and the complexity of real-world anomalies. In this paper, we propose a foundation model-based anomaly synthesis pipeline (FMAS) that generates highly realistic anomalous samples without fine-tuning or class-specific training. Motivated by the distinct frequency-domain characteristics of anomalies, we introduce aWavelet Domain Attention Module (WDAM), which exploits adaptive sub-band processing to enhance anomaly feature extraction. The combination of FMAS and WDAM significantly improves anomaly detection sensitivity while maintaining computational efficiency. Comprehensive experiments on MVTec AD and VisA datasets demonstrate that WDAM, as a plug-and-play module, achieves substantial performance gains against existing baselines.