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

29 Jun 2020  ·  Jihun Yi, Sungroh Yoon ·

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.

PDF Abstract

Datasets


Results from the Paper


Ranked #8 on Anomaly Detection on BTAD (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Anomaly Detection BTAD PatchSVDD Segmentation AUROC 93.1 # 8
Anomaly Detection MVTec AD Patch-SVDD Detection AUROC 92.1 # 74
Segmentation AUROC 95.7 # 68
FPS 2.1 # 19

Methods


No methods listed for this paper. Add relevant methods here