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

Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation

About

In this paper, we address the problem of image anomaly detection and segmentation. Anomaly detection involves making a binary decision as to whether an input image contains an anomaly, and anomaly segmentation aims to locate the anomaly on the pixel level. Support vector data description (SVDD) is a long-standing algorithm used for an anomaly detection, and we extend its deep learning variant to the patch-based method using self-supervised learning. This extension enables anomaly segmentation and improves detection performance. As a result, anomaly detection and segmentation performances measured in AUROC on MVTec AD dataset increased by 9.8% and 7.0%, respectively, compared to the previous state-of-the-art methods. Our results indicate the efficacy of the proposed method and its potential for industrial application. Detailed analysis of the proposed method offers insights regarding its behavior, and the code is available online.

Jihun Yi, Sungroh Yoon• 2020

Related benchmarks

TaskDatasetResultRank
Anomaly LocalizationMVTec AD
Pixel AUROC96.7
369
Anomaly DetectionMVTec-AD (test)
I-AUROC93.2
226
Anomaly LocalizationMVTec-AD (test)
Pixel AUROC95.7
181
Anomaly SegmentationMVTec-AD (test)
AUROC (Pixel)95.7
85
Anomaly DetectionMVTec AD
Overall AUROC92.1
83
Anomaly LocalizationMVTec
AUC98.1
70
Anomaly DetectionMVTec AD 1.0 (test)
Image AUROC72.1
57
Anomaly DetectionMVTecAD (test)
Bottle Score99
55
Anomaly LocalizationMVTec AD 1.0 (test)
AUROC (Pixel)95.7
47
Anomaly DetectionBrainMRI (test)
AUC-ROC0.795
45
Showing 10 of 33 rows

Other info

Code

Follow for update