Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Prototypical Residual Networks for Anomaly Detection and Localization

About

Anomaly detection and localization are widely used in industrial manufacturing for its efficiency and effectiveness. Anomalies are rare and hard to collect and supervised models easily over-fit to these seen anomalies with a handful of abnormal samples, producing unsatisfactory performance. On the other hand, anomalies are typically subtle, hard to discern, and of various appearance, making it difficult to detect anomalies and let alone locate anomalous regions. To address these issues, we propose a framework called Prototypical Residual Network (PRN), which learns feature residuals of varying scales and sizes between anomalous and normal patterns to accurately reconstruct the segmentation maps of anomalous regions. PRN mainly consists of two parts: multi-scale prototypes that explicitly represent the residual features of anomalies to normal patterns; a multisize self-attention mechanism that enables variable-sized anomalous feature learning. Besides, we present a variety of anomaly generation strategies that consider both seen and unseen appearance variance to enlarge and diversify anomalies. Extensive experiments on the challenging and widely used MVTec AD benchmark show that PRN outperforms current state-of-the-art unsupervised and supervised methods. We further report SOTA results on three additional datasets to demonstrate the effectiveness and generalizability of PRN.

Hui Zhang, Zuxuan Wu, Zheng Wang, Zhineng Chen, Yu-Gang Jiang• 2022

Related benchmarks

TaskDatasetResultRank
Anomaly LocalizationMVTec AD
Pixel AUROC99
369
Anomaly DetectionMVTec-AD (test)
I-AUROC99.4
226
Anomaly LocalizationMVTec-AD (test)
Pixel AUROC99
181
Anomaly DetectionMVTec AD 1.0 (test)--
57
Anomaly LocalizationMVTec AD 1.0 (test)--
47
Anomaly DetectionMVTec AD
AUROC (Image-level)99.4
45
Anomaly DetectionKSDD2
APdet78.6
14
Anomaly LocalizationKolektorSDD2 (test)
AP72.5
13
Anomaly DetectionNVIDIA Tesla V100S
Parameters (M)88
12
Anomaly LocalizationBTAD 03
AP57.4
10
Showing 10 of 21 rows

Other info

Follow for update