English

CNC: Cross-modal Normality Constraint for Unsupervised Multi-class Anomaly Detection

Computer Vision and Pattern Recognition 2025-01-03 v1 Artificial Intelligence Machine Learning

Abstract

Existing unsupervised distillation-based methods rely on the differences between encoded and decoded features to locate abnormal regions in test images. However, the decoder trained only on normal samples still reconstructs abnormal patch features well, degrading performance. This issue is particularly pronounced in unsupervised multi-class anomaly detection tasks. We attribute this behavior to over-generalization(OG) of decoder: the significantly increasing diversity of patch patterns in multi-class training enhances the model generalization on normal patches, but also inadvertently broadens its generalization to abnormal patches. To mitigate OG, we propose a novel approach that leverages class-agnostic learnable prompts to capture common textual normality across various visual patterns, and then apply them to guide the decoded features towards a normal textual representation, suppressing over-generalization of the decoder on abnormal patterns. To further improve performance, we also introduce a gated mixture-of-experts module to specialize in handling diverse patch patterns and reduce mutual interference between them in multi-class training. Our method achieves competitive performance on the MVTec AD and VisA datasets, demonstrating its effectiveness.

Keywords

Cite

@article{arxiv.2501.00346,
  title  = {CNC: Cross-modal Normality Constraint for Unsupervised Multi-class Anomaly Detection},
  author = {Xiaolei Wang and Xiaoyang Wang and Huihui Bai and Eng Gee Lim and Jimin Xiao},
  journal= {arXiv preprint arXiv:2501.00346},
  year   = {2025}
}

Comments

Accepted by AAAI 2025

R2 v1 2026-06-28T20:53:12.504Z