A Contrastive Learning-Guided Confident Meta-learning for Zero Shot Anomaly Detection

TL;DR

This paper introduces CoZAD, a zero-shot anomaly detection framework that combines contrastive learning, meta-learning, and confidence-based weighting to improve detection accuracy in industrial and medical applications with limited data.

Contribution

The proposed CoZAD framework innovatively integrates confidence-weighted training, contrastive feature learning, and meta-learning for effective zero-shot anomaly detection without reliance on vision-language models.

Findings

Achieved state-of-the-art results on 6 out of 7 industrial benchmarks.

Demonstrated high accuracy on texture-rich datasets with 99.2% I-AUROC.

Enabled rapid domain adaptation and pixel-level localization.

Abstract

Industrial and medical anomaly detection faces critical challenges from data scarcity and prohibitive annotation costs, particularly in evolving manufacturing and healthcare settings. To address this, we propose CoZAD, a novel zero-shot anomaly detection framework that integrates soft confident learning with meta-learning and contrastive feature representation. Unlike traditional confident learning that discards uncertain samples, our method assigns confidence-based weights to all training data, preserving boundary information while emphasizing prototypical normal patterns. The framework quantifies data uncertainty through IQR-based thresholding and model uncertainty via covariance based regularization within a Model-Agnostic Meta-Learning. Contrastive learning creates discriminative feature spaces where normal patterns form compact clusters, enabling rapid domain adaptation. Comprehensive evaluation across 10 datasets spanning industrial and medical domains demonstrates state-of-the-art performance, outperforming existing methods on 6 out of 7 industrial benchmarks with notable improvements on texture-rich datasets (99.2% I-AUROC on DTD-Synthetic, 97.2% on BTAD) and pixellevel localization (96.3% P-AUROC on MVTec-AD). The framework eliminates dependence on vision-language alignments or model ensembles, making it valuable for resourceconstrained environments requiring rapid deployment.