LaRP-CLIP: Layer-Aware Refinement with Prototype Guidance for Zero-Shot Anomaly Detection

Export Citation

Fang, X, Chen, Y, Lin, Q, Yang, K and Lee, GM orcid iconORCID: 0000-0002-2155-5553 LaRP-CLIP: Layer-Aware Refinement with Prototype Guidance for Zero-Shot Anomaly Detection. Computers, Materials and Continua. ISSN 1546-2218 (Accepted)

[thumbnail of CMC-84208-Manuscript-123326-1.pdf]
Preview
 Text
CMC-84208-Manuscript-123326-1.pdf - Accepted Version
Available under License Creative Commons Attribution.
Download (1MB) | Preview

Abstract

The deployment of supervised anomaly detection is typically limited by the high cost of annotation, privacy constraints, and the scarcity of anomalous samples. These constraints have motivated the use of vision-language pre-trained models for zero-shot anomaly detection. However, existing CLIP-based methods still face three limitations: a shared set of prompts is applied across feature layers, anomaly maps are fused by fixed strategies, and image-level anomaly scores are determined solely by global image-text similarity. These limitations reduce the accuracy of pixel-level localization and weaken the reliability of image-level anomaly prediction. To overcome these limitations, LaRP-CLIP is proposed. It introduces layer-aware prompt decoupling to better match feature layers with different semantic characteristics, adaptive fusion with error-prior-guided local refinement to produce cleaner and more precise anomaly maps, and a prototype branch to improve image-level scoring. Experiments on four industrial datasets and seven medical datasets show that LaRP-CLIP achieves strong performance in both image-level detection and pixel-level localization.

Item Type: Article
Uncontrolled Keywords: Zero-shot anomaly detection; Vision-language models; Layer-aware prompts; 0103 Numerical and Computational Mathematics; 0912 Materials Engineering; 0915 Interdisciplinary Engineering; Applied Mathematics; 40 Engineering; 46 Information and computing sciences
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Computer Science and Mathematics
Publisher: Tech Science Press
Date of acceptance: 22 May 2026
Date of first compliant Open Access: 22 May 2026
Date Deposited: 22 May 2026 14:26
Last Modified: 22 May 2026 14:26
URI: https://researchonline.ljmu.ac.uk/id/eprint/28630
View Item View Item
CORE (COnnecting REpositories)