Towards Total Recall in Industrial Anomaly Detection

Latha Pemula

Abstract:

Being able to spot defective parts is a critical component
in large-scale industrial manufacturing. A particular chal-
lenge that we address in this work is the cold-start problem:
fit a model using nominal (non-defective) example images
only. While handcrafted solutions per class are possible,
the goal is to build systems that work well simultaneously
on many different tasks automatically. The best peform-
ing approaches combine embeddings from ImageNet mod-
els with an outlier detection model. In this paper, we extend
on this line of work and propose PatchCore, which uses
a maximally representative memory bank of nominal patch-
features. PatchCore offers competitive inference times while
achieving state-of-the-art performance for both detection
and localization. On the challenging, widely used MVTec
AD benchmark PatchCore achieves an image-level anomaly
detection AUROC score of up to 99.6%, more than halving
the error compared to the next best competitor. We fur-
ther report competitive results on two additional datasets
and also find competitive results in the few samples regime.