WMoE-CLIP: Wavelet-Enhanced Mixture-of-Experts Prompt Learning for Zero-Shot Anomaly Detection

TL;DR

This paper introduces a wavelet-enhanced mixture-of-experts prompt learning approach for zero-shot anomaly detection, improving semantic understanding and multi-frequency feature extraction to better identify unseen anomalies.

Contribution

It proposes a novel wavelet-enhanced prompt learning framework with a semantic-aware mixture-of-experts module, advancing zero-shot anomaly detection beyond fixed prompts and spatial features.

Findings

Outperforms existing methods on 14 industrial and medical datasets.

Effectively captures complex semantics and multi-frequency features.

Enhances zero-shot anomaly detection accuracy.

Abstract

Vision-language models have recently shown strong generalization in zero-shot anomaly detection (ZSAD), enabling the detection of unseen anomalies without task-specific supervision. However, existing approaches typically rely on fixed textual prompts, which struggle to capture complex semantics, and focus solely on spatial-domain features, limiting their ability to detect subtle anomalies. To address these challenges, we propose a wavelet-enhanced mixture-of-experts prompt learning method for ZSAD. Specifically, a variational autoencoder is employed to model global semantic representations and integrate them into prompts to enhance adaptability to diverse anomaly patterns. Wavelet decomposition extracts multi-frequency image features that dynamically refine textual embeddings through cross-modal interactions. Furthermore, a semantic-aware mixture-of-experts module is introduced to aggregate contextual information. Extensive experiments on 14 industrial and medical datasets demonstrate the effectiveness of the proposed method.