Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore

TL;DR

This paper introduces GraphCore, a novel graph-based model utilizing rotation-invariant features to significantly enhance fewshot anomaly detection performance in industrial vision tasks, outperforming existing methods.

Contribution

The paper proposes VIIF, a new rotation-invariant feature, and GraphCore, a model that leverages VIIF for improved unsupervised fewshot anomaly detection in industrial images.

Findings

GraphCore outperforms SOTA models with up to 25.5% AUC increase.

VIIF reduces redundant features and enhances anomaly discrimination.

The approach is effective across different fewshot settings on MVTec AD and MPDD datasets.

Abstract

In the area of fewshot anomaly detection (FSAD), efficient visual feature plays an essential role in memory bank M-based methods. However, these methods do not account for the relationship between the visual feature and its rotated visual feature, drastically limiting the anomaly detection performance. To push the limits, we reveal that rotation-invariant feature property has a significant impact in industrial-based FSAD. Specifically, we utilize graph representation in FSAD and provide a novel visual isometric invariant feature (VIIF) as anomaly measurement feature. As a result, VIIF can robustly improve the anomaly discriminating ability and can further reduce the size of redundant features stored in M by a large amount. Besides, we provide a novel model GraphCore via VIIFs that can fast implement unsupervised FSAD training and can improve the performance of anomaly detection. A comprehensive evaluation is provided for comparing GraphCore and other SOTA anomaly detection models under our proposed fewshot anomaly detection setting, which shows GraphCore can increase average AUC by 5.8%, 4.1%, 3.4%, and 1.6% on MVTec AD and by 25.5%, 22.0%, 16.9%, and 14.1% on MPDD for 1, 2, 4, and 8-shot cases, respectively.