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

2026-03-03

AI Summary

This work addresses the challenge of industrial anomaly detection, which is hindered by the scarcity and morphological complexity of real-world anomalous samples. To overcome this limitation, the authors propose a Foundation Model-based Anomaly Synthesis (FMAS) pipeline that generates highly realistic anomaly samples without requiring fine-tuning or class-specific training. Furthermore, they introduce a plug-and-play Wavelet Domain Attention Module (WDAM) that adaptively enhances subband features in the frequency domain that are characteristic of anomalies. By integrating foundation model–driven synthesis, wavelet transforms, and attention mechanisms, the proposed method achieves state-of-the-art performance on the MVTec AD and VisA benchmarks, significantly improving detection sensitivity while maintaining computational efficiency.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Computer Vision: Other Foundations of Computer Vision
• Machine Learning: Deep Neural Architectures and Foundation Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• anomaly detection
• industrial anomaly
• anomalous samples scarcity
• real-world anomalies
• frequency-domain characteristics

Innovation

• Foundation Model
• Anomaly Synthesis
• Wavelet Domain Attention
• Plug-and-Play Module
• Industrial Anomaly Detection