Uni-RCM: Unified Reference-Guided Cross-Modal Mapping for Multi-Class Anomaly Detection
IEEE Signal Processing Letters · 2026 · 33 · 2265-2269
DOI: 10.1109/lsp.2026.3698767 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Yangchen Wu und 1 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Basic and Applied Basic Research Foundation of Guangdong Province, Guangzhou Municipal Science and Technology Project.
Abstract (Originalsprache)
Multi-modal industrial anomaly detection typically relies on separate models for each product category, fundamentally limiting practical scalability. When shifting to a unified paradigm that handles diverse classes simultaneously, detection accuracy often degrades due to inter-class interference and feature manifold confusion. To overcome these challenges, we propose a Unified Reference guided Cross-modal Mapping framework, named Uni-RCM. At its core, we propose a reference guide block to dynamically filter out category-specific noise by introducing a learnable reference feature, which captures the commonalities across different modalities. Besides, an offline residual quantizer is proposed to characterize the normal distribution by multiple cascaded codebooks. Extensive evaluations on the MVTec-3D AD dataset demonstrate the state-of-the-art performance in the challenging multi-class setting and in terms of image-level detection and pixel-level localization.
Förderung
- National Natural Science Foundation of China
- Basic and Applied Basic Research Foundation of Guangdong Province
- Guangzhou Municipal Science and Technology Project
Zitieren
APA
Wu, Y., & Xie, H. (2026). Uni-RCM: Unified Reference-Guided Cross-Modal Mapping for Multi-Class Anomaly Detection. IEEE Signal Processing Letters, 33, 2265-2269. https://doi.org/10.1109/lsp.2026.3698767
Vancouver
Wu Y, Xie H. Uni-RCM: Unified Reference-Guided Cross-Modal Mapping for Multi-Class Anomaly Detection. IEEE Signal Processing Letters. 2026;33:2265-2269. doi:10.1109/lsp.2026.3698767
BibTeX
@article{Wu2026,
author = {Wu, Yangchen and Xie, Huiqiang},
title = {Uni-RCM: Unified Reference-Guided Cross-Modal Mapping for Multi-Class Anomaly Detection},
journal = {IEEE Signal Processing Letters},
year = {2026},
volume = {33},
pages = {2265--2269},
doi = {10.1109/lsp.2026.3698767}
}
EUVIMED