Zero-Shot Anomaly Detection via Learnable Complementary Prompts and Cross-Modal Interaction
TL;DR
Extensive experiments conducted on ten real-world industrial anomaly segmentation datasets demonstrate the superior performance of LCPCLIP in detecting anomalies without any prior knowledge of the dataset categories, which sets a new benchmark for adaptability and generalization in industrial applications.
Abstract
Anomaly detection is a critical task with broad applications in industrial and medical domains. In this paper, we propose LCPCLIP, a novel model designed to address zero-shot anomaly detection by leveraging the power of learnable complementary anomaly prompts. Unlike traditional approaches that rely on pre-defined category labels or extensive manual prompt, LCPCLIP introduces multiple learnable anomaly prompts optimized through complementary anomaly prompt loss, which can ensure orthogonality and diversity in learned features. Meanwhile, it incorporates a Dynamic Category Feature Embedding (DCFE) module, which fuses category and global feature information into text prompts without requiring explicit category labels. Moreover, a Vision-Text Cross-Attention (VTCA) module is proposed to enhances the interaction between text prompts and fine-grained local features. Extensive experiments conducted on ten real-world industrial anomaly segmentation datasets demonstrate the superior performance of LCPCLIP in detecting anomalies without any prior knowledge of the dataset categories. It sets a new benchmark for adaptability and generalization in industrial applications. Our code and pre-trained models are available at https://github.com/rougasuki/LCPCLIP .