- About Journal
- Articles Online
- For Authors
- For Referees
- 个人中心
- 退出登录
浏览全部资源
扫码关注微信
- About Journal
- Articles Online
- For Authors
- For Referees
Abnormity detection based on fusion feature distribution learning and image reconstruction
- Chinese Journal of Liquid Crystals and Displays Vol. 39, Issue 8, Pages: 1116-1127(2024)
- 作者机构：
武汉科技大学 信息科学与工程学院， 湖北 武汉 430070
- 作者简介：
- 基金信息：National Natural Science Foundation of China(62173262)
DOI：10.37188/CJLCD.2023-0304
CLC： TP391.4Received：19 September 2023，
Revised：12 October 2023，
Published：05 August 2024
- 稿件说明：
移动端阅览
ZHU Siyu, ZHU Lei, WANG Wenwu, et al. Abnormity detection based on fusion feature distribution learning and image reconstruction[J]. Chinese journal of liquid crystals and displays, 2024, 39(8): 1116-1127.
ZHU Siyu, ZHU Lei, WANG Wenwu, et al. Abnormity detection based on fusion feature distribution learning and image reconstruction[J]. Chinese journal of liquid crystals and displays, 2024, 39(8): 1116-1127. DOI： 10.37188/CJLCD.2023-0304.
摘要
无监督学习是当前工业产品缺陷检测领域的主流研究方向，目前主要分为基于重建和基于特征的两类方法。前者构建基于内容感知的映射以将异常区域映射为正常区域并通过残差图像来检测缺陷，注重于图像整体的表现。后者利用高层语义特征以实现定位异常，更加注重图像细节呈现。根据两种方法的优缺点，本文提出一种基于特征与重建融合的方法，有效结合两者优点互补其不足并实现统一的端到端的学习与推理。首先训练一个重建模型，然后采用归一化流模型以充分学习输入正常样本的高可能性数据概率分布，使其与重建模型相融合，有效地提高重建模型缺陷检测以及缺陷定位的准确率。在广泛使用的MVTec AD数据集上，提出的融合模型的平均图像级AUROC达到了98.7%，平均像素级AUROC达到了94.2%，特别地，相比单一重建模型提升了3.3%。提出的特征与重建网络融合模型显著提高了重建网络部分对于缺陷定位的不足，使结果更为精确。
Abstract
Unsupervised learning is the main research direction in the field of industrial product defect detection at present， and it is mainly divided into two types of methods： reconstruction based and feature based methods. The former constructs content-aware mappings to map abnormal regions into normal regions and detect defects through residual images， focusing on overall performance of the images. The latter uses high-level semantic features to achieve positioning exceptions and pay more attention to image detail presentation. According to the advantages and disadvantages of the two methods， a method is proposed based on the fusion of characteristics and reconstruction， which effectively combines advantages of the two methods to complement their shortcomings and realize unified end-to-end learning and reasoning. Ａreconstructed model is trained firstly， then a normalized flow model is adopted to fully learn the probability distribution of high probability data of input normal samples， and it is integrated with the reconstructed model to effectively improve the accuracy of defect detection and defect positioning of the reconstructed model. On the widely used MVTec AD data set， the average image level AUROC of the proposed fusion model reaches 98.7%， the average pixel-level AUROC reaches 94.2%， in particular， an increase of 3.3% compared to a single reconstruction model. The convergence model of characteristics and proposed reconstruction network has significantly improved the shortcomings of defect positioning in the reconstruction network part， which makes experimental results more accurate.
关键词
Keywords
references
NAYAK R ， PATI U C ， DAS S K . A comprehensive review on deep learning-based methods for video anomaly detection ［J］. Image and Vision Computing ， 2021 ， 106 ： 104078 . doi: 10.1016/j.imavis.2020.104078 http://dx.doi.org/10.1016/j.imavis.2020.104078
PATCHA A ， PARK J M . An overview of anomaly detection techniques： existing solutions and latest technological trends ［J］. Computer Networks ， 2007 ， 51 （ 12 ）： 3448 - 3470 . doi: 10.1016/j.comnet.2007.02.001 http://dx.doi.org/10.1016/j.comnet.2007.02.001
GONG D ， LIU L Q ， LE V ， et al . Memorizing normality to detect anomaly： memory-augmented deep autoencoder for unsupervised anomaly detection ［C］// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision （ICCV） . Seoul， Korea ： IEEE ， 2019 ： 1705 - 1714 . doi: 10.1109/iccv.2019.00179 http://dx.doi.org/10.1109/iccv.2019.00179
BERGMANN P ， FAUSER M ， SATTLEGGER D ， et al . Uninformed Students： student-teacher anomaly detection with discriminative latent embeddings ［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . Seattle， WA， USA ： IEEE ， 2020 ： 4182 - 4191 . doi: 10.1109/cvpr42600.2020.00424 http://dx.doi.org/10.1109/cvpr42600.2020.00424
KINGMA D P ， WELLING M . Auto-encoding variational Bayes ［C］// Proceedings of the 2nd International Conference on Learning Representations . Banff， AB， Canada ： Curran Associates Inc. ， 2014 .
SAKURADA M ， YAIRI T . Anomaly detection using autoencoders with nonlinear dimensionality reduction ［C］// Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis . Gold Coast， Australia QLD， Australia ： Association for Computing Machinery ， 2014 ： 4 - 11 . doi: 10.1145/2689746.2689747 http://dx.doi.org/10.1145/2689746.2689747
CAO V L ， NICOLAU M ， MCDERMOTT J . A hybrid autoencoder and density estimation model for anomaly detection ［C］// Proceedings of the 14th International Conference on Parallel Problem Solving from Nature . Edinburgh， UK ： Springer ， 2016 ： 717 - 726 . doi: 10.1007/978-3-319-45823-6_67 http://dx.doi.org/10.1007/978-3-319-45823-6_67
SABOKROU M ， KHALOOEI M ， FATHY M ， et al . Adversarially learned one-class classifier for novelty detection ［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . Salt Lake City， UT， USA ： IEEE ， 2018 ： 3379 - 3388 . doi: 10.1109/cvpr.2018.00356 http://dx.doi.org/10.1109/cvpr.2018.00356
COHEN N ， HOSHEN Y . Sub-image anomaly detection with deep pyramid correspondences ［J/OL］. arXiv ， 2020 ： 2005 . 02357 . doi: 10.48550/arXiv.2005.02357 http://dx.doi.org/10.48550/arXiv.2005.02357
DEFARD T ， SETKOV A ， LOESCH A ， et al . PaDiM： a patch distribution modeling framework for anomaly detection and localization ［C］// Proceedings of the ICPR International Workshops and Challenges Pattern Recognition . Online ： Springer ， 2021 ： 475 - 489 . doi: 10.1007/978-3-030-68799-1_35 http://dx.doi.org/10.1007/978-3-030-68799-1_35
RUDOLPH M ， WANDT B ， ROSENHAHN B . Same but DifferNet： semi-supervised defect detection with normalizing flows ［C］// Proceedings of the 2021 IEEE Winter Conference on Applications of Computer Vision （WACV） . Waikoloa， HI， USA ： IEEE ， 2021 ： 1906 - 1915 . doi: 10.1109/wacv48630.2021.00195 http://dx.doi.org/10.1109/wacv48630.2021.00195
LIU P J ， ZHANG H Z ， ZHANG K ， et al . Multi-level wavelet-CNN for image restoration ［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops （CVPR） . Salt Lake City， UT， USA ： IEEE ， 2018 ： 773 - 782 . doi: 10.1109/cvprw.2018.00121 http://dx.doi.org/10.1109/cvprw.2018.00121
REZENDE D J ， MOHAMED S . Variational inference with normalizing flows ［C］// Proceedings of the 32nd International Conference on Machine Learning . Lille， France ： JMLR.org ， 2015 ： 1530 - 1538 .
BERGMANN P ， FAUSER M ， SATTLEGGER D ， et al . MVTec AD—A comprehensive real-world dataset for unsupervised anomaly detection ［C］// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach， CA， USA ： IEEE ， 2019 ： 9584 - 9592 . doi: 10.1109/cvpr.2019.00982 http://dx.doi.org/10.1109/cvpr.2019.00982
KINGMA D P ， BA J . Adam： a method for stochastic optimization ［C］// Proceedings of the 3rd International Conference on Learning Representations . San Diego， CA， USA ： Curran Associates Inc. ， 2015 .
HOU J L ， ZHANG Y Y ， ZHONG Q Y ， et al . Divide-and-assemble： learning block-wise memory for unsupervised anomaly detection ［C］// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision （ICCV） . Montreal， QC， Canada ： IEEE ， 2021 ： 8771 - 8780 . doi: 10.1109/iccv48922.2021.00867 http://dx.doi.org/10.1109/iccv48922.2021.00867
ZAVRTANIK V ， KRISTAN M ， SKOČAJ D . DRAEM—A discriminatively trained reconstruction embedding for surface anomaly detection ［C］// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision （ICCV） . Montreal， QC， Canada ： IEEE ， 2021 ： 8310 - 8319 . doi: 10.1109/iccv48922.2021.00822 http://dx.doi.org/10.1109/iccv48922.2021.00822
HUANG C Q ， XU Q W ， WANG Y F ， et al . Self-supervised masking for unsupervised anomaly detection and localization ［J］. IEEE Transactions on Multimedia ， 2023 ， 25 ： 4426 - 4438 . doi: 10.1109/tmm.2022.3175611 http://dx.doi.org/10.1109/tmm.2022.3175611
LI C L ， SOHN K ， YOON J ， et al . CutPaste： self-supervised learning for anomaly detection and localization ［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . Nashville， TN， USA ： IEEE ， 2021 ： 9659 - 9669 . doi: 10.1109/cvpr46437.2021.00954 http://dx.doi.org/10.1109/cvpr46437.2021.00954
GUDOVSKIY D ， ISHIZAKA S ， KOZUKA K . CFLOW-AD： real-time unsupervised anomaly detection with localization via conditional normalizing flows ［C］// Proceedings of the 2022 IEEE/CVF Winter Conference on Applications of Computer Vision （WACV） . Waikoloa， HI， USA ： IEEE ， 2022 ： 1819 - 1828 . doi: 10.1109/wacv51458.2022.00188 http://dx.doi.org/10.1109/wacv51458.2022.00188
0
Views
103
下载量
0
CSCD
- L-PDFDownload
- WORDDownload
- Meta-XMLDownload
- BibTeXDownload
- EndnoteDownload
- RefMan Download
- NoteExpressDownload
- NoteFirstDownload
Publicity Resources
Related Articles
Related Author
Related Institution
- Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
- Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
- Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17
京公网安备11010802024621 - It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
- Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
