Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection

被引:166
作者
Rudolph, Marco [1 ]
Wehrbein, Tom [1 ]
Rosenhahn, Bodo [1 ]
Wandt, Bastian [2 ]
机构
[1] Leibniz Univ Hannover, Hannover, Germany
[2] Univ British Columbia, Vancouver, BC, Canada
来源
2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022) | 2022年
关键词
D O I
10.1109/WACV51458.2022.00189
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In industrial manufacturing processes, errors frequently occur at unpredictable times and in unknown manifestations. We tackle the problem of automatic defect detection without requiring any image samples of defective parts. Recent works model the distribution of defect-free image data, using either strong statistical priors or overly simplified data representations. In contrast, our approach handles fine-grained representations incorporating the global and local image context while flexibly estimating the density. To this end, we propose a novel fully convolutional cross-scale normalizing flow (CS-Flow) that jointly processes multiple feature maps of different scales. Using normalizing flows to assign meaningful likelihoods to input samples allows for efficient defect detection on image-level. Moreover, due to the preserved spatial arrangement the latent space of the normalizing flow is interpretable which enables to localize defective regions in the image. Our work sets a new state-of-the-art in image-level defect detection on the benchmark datasets Magnetic Tile Defects and MVTec AD showing a 100% AUROC on 4 out of 15 classes.
引用
收藏
页码:1829 / 1838
页数:10
相关论文
共 42 条
[1]   GANomaly: Semi-supervised Anomaly Detection via Adversarial Training [J].
Akcay, Samet ;
Atapour-Abarghouei, Amir ;
Breckon, Toby P. .
COMPUTER VISION - ACCV 2018, PT III, 2019, 11363 :622-637
[2]  
Andrews Jerone, 2019, NEURIPS
[3]  
Ardizzone Lynton, 2019, ARXIV190702392
[4]  
Awiszus Maren, 2020, P AAAI C ARTIFICIAL, V16, P10
[5]  
Bergmann P., 2019, VISIGRAPP
[6]   MVTec AD - A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection [J].
Bergmann, Paul ;
Fauser, Michael ;
Sattlegger, David ;
Steger, Carsten .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :9584-9592
[7]  
Cheng HQ, 2020, PROCEEDINGS OF 2020 IEEE 4TH INFORMATION TECHNOLOGY, NETWORKING, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (ITNEC 2020), P987, DOI [10.1109/itnec48623.2020.9085163, 10.1109/ITNEC48623.2020.9085163]
[8]  
Defard Thomas, 2021, ICPR INT WORKSH CHAL
[9]  
Deng J, 2009, PROC CVPR IEEE, P248, DOI 10.1109/CVPRW.2009.5206848
[10]  
DIAS MLD, 2020, ARXIV200405958