N-pad : Neighboring Pixel-based Industrial Anomaly Detection

TL;DR

N-pad introduces a neighbor-aware anomaly detection method for industrial images that leverages local pixel neighborhoods to improve defect identification, achieving state-of-the-art results on MVTec-AD.

Contribution

The paper proposes a novel neighbor-based approach for industrial anomaly detection that incorporates local pixel neighborhoods into the model training and evaluation process.

Findings

Achieved AUROC of 99.37 for anomaly detection on MVTec-AD.

Reduced error by 34% compared to previous models.

Validated robustness across various experimental settings.

Abstract

Identifying defects in the images of industrial products has been an important task to enhance quality control and reduce maintenance costs. In recent studies, industrial anomaly detection models were developed using pre-trained networks to learn nominal representations. To employ the relative positional information of each pixel, we present \textit{\textbf{N-pad}}, a novel method for anomaly detection and segmentation in a one-class learning setting that includes the neighborhood of the target pixel for model training and evaluation. Within the model architecture, pixel-wise nominal distributions are estimated by using the features of neighboring pixels with the target pixel to allow possible marginal misalignment. Moreover, the centroids from clusters of nominal features are identified as a representative nominal set. Accordingly, anomaly scores are inferred based on the Mahalanobis distances and Euclidean distances between the target pixel and the estimated distributions or the centroid set, respectively. Thus, we have achieved state-of-the-art performance in MVTec-AD with AUROC of 99.37 for anomaly detection and 98.75 for anomaly segmentation, reducing the error by 34\% compared to the next best performing model. Experiments in various settings further validate our model.