Prior Normality Prompt Transformer for Multi-class Industrial Image Anomaly Detection

TL;DR

This paper introduces the Prior Normality Prompt Transformer (PNPT), a novel model that enhances multi-class industrial image anomaly detection by integrating normal semantics prompts to improve discrimination between normal and abnormal instances.

Contribution

The study proposes the PNPT method, which incorporates normality prompts into a dual-stream transformer architecture, addressing the challenge of identical shortcut learning in multi-class anomaly detection.

Findings

PNPT outperforms existing methods on benchmark datasets.

The model effectively mitigates the 'identical shortcut' problem.

Experimental results demonstrate superior detection accuracy in real-world applications.

Abstract

Image anomaly detection plays a pivotal role in industrial inspection. Traditional approaches often demand distinct models for specific categories, resulting in substantial deployment costs. This raises concerns about multi-class anomaly detection, where a unified model is developed for multiple classes. However, applying conventional methods, particularly reconstruction-based models, directly to multi-class scenarios encounters challenges such as identical shortcut learning, hindering effective discrimination between normal and abnormal instances. To tackle this issue, our study introduces the Prior Normality Prompt Transformer (PNPT) method for multi-class image anomaly detection. PNPT strategically incorporates normal semantics prompting to mitigate the "identical mapping" problem. This entails integrating a prior normality prompt into the reconstruction process, yielding a dual-stream model. This innovative architecture combines normal prior semantics with abnormal samples, enabling dual-stream reconstruction grounded in both prior knowledge and intrinsic sample characteristics. PNPT comprises four essential modules: Class-Specific Normality Prompting Pool (CS-NPP), Hierarchical Patch Embedding (HPE), Semantic Alignment Coupling Encoding (SACE), and Contextual Semantic Conditional Decoding (CSCD). Experimental validation on diverse benchmark datasets and real-world industrial applications highlights PNPT's superior performance in multi-class industrial anomaly detection.