Normality Prior Guided Multi-Semantic Fusion Network for Unsupervised Image Anomaly Detection

TL;DR

This paper introduces a normality prior guided multi-semantic fusion network that enhances unsupervised image anomaly detection by incorporating global semantic features of normal samples, achieving state-of-the-art results.

Contribution

It proposes a novel multi-semantic fusion approach guided by normality priors, utilizing a vision-language network and semantic codebooks to improve anomaly detection accuracy.

Findings

Achieves state-of-the-art performance on MVTec LOCO AD dataset

Improves pixel-sPRO by 5.7%

Enhances image-AUROC by 2.6%

Abstract

Recently, detecting logical anomalies is becoming a more challenging task compared to detecting structural ones. Existing encoder decoder based methods typically compress inputs into low-dimensional bottlenecks on the assumption that the compression process can effectively suppress the transmission of logical anomalies to the decoder. However, logical anomalies present a particular difficulty because, while their local features often resemble normal semantics, their global semantics deviate significantly from normal patterns. Thanks to the generalisation capabilities inherent in neural networks, these abnormal semantic features can propagate through low-dimensional bottlenecks. This ultimately allows the decoder to reconstruct anomalous images with misleading fidelity. To tackle the above challenge, we propose a novel normality prior guided multi-semantic fusion network for unsupervised anomaly detection. Instead of feeding the compressed bottlenecks to the decoder directly, we introduce the multi-semantic features of normal samples into the reconstruction process. To this end, we first extract abstract global semantics of normal cases by a pre-trained vision-language network, then the learnable semantic codebooks are constructed to store representative feature vectors of normal samples by vector quantisation. Finally, the above multi-semantic features are fused and employed as input to the decoder to guide the reconstruction of anomalies to approximate normality. Extensive experiments are conducted to validate the effectiveness of our proposed method, and it achieves the SOTA performance on the MVTec LOCO AD dataset with improvements of 5.7% in pixel-sPRO and 2.6% in image-AUROC. The source code is available at https://github.com/Xmh-L/NPGMF.