Multi-Cue Anomaly Detection and Localization under Data Contamination

TL;DR

This paper presents a robust anomaly detection framework that effectively integrates limited anomaly supervision and adaptive learning to improve detection, localization, and interpretability in contaminated industrial datasets.

Contribution

It introduces a composite anomaly scoring method and adaptive instance weighting to handle contaminated data with limited labeled anomalies.

Findings

Outperforms state-of-the-art methods on MVTec and VisA benchmarks.

Achieves high detection and localization accuracy under data contamination.

Provides interpretable visual evidence of anomalies.

Abstract

Visual anomaly detection in real-world industrial settings faces two major limitations. First, most existing methods are trained on purely normal data or on unlabeled datasets assumed to be predominantly normal, presuming the absence of contamination, an assumption that is rarely satisfied in practice. Second, they assume no access to labeled anomaly samples, limiting the model from learning discriminative characteristics of true anomalies. Therefore, these approaches often struggle to distinguish anomalies from normal instances, resulting in reduced detection and weak localization performance. In real-world applications, where training data are frequently contaminated with anomalies, such methods fail to deliver reliable performance. In this work, we propose a robust anomaly detection framework that integrates limited anomaly supervision into the adaptive deviation learning paradigm. We introduce a composite anomaly score that combines three complementary components: a deviation score capturing statistical irregularity, an entropy-based uncertainty score reflecting predictive inconsistency, and a segmentation-based score highlighting spatial abnormality. This unified scoring mechanism enables accurate detection and supports gradient-based localization, providing intuitive and explainable visual evidence of anomalous regions. Following the few-anomaly paradigm, we incorporate a small set of labeled anomalies during training while simultaneously mitigating the influence of contaminated samples through adaptive instance weighting. Extensive experiments on the MVTec and VisA benchmarks demonstrate that our framework outperforms state-of-the-art baselines and achieves strong detection and localization performance, interpretability, and robustness under various levels of data contamination.