Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (11): 3587-3594.DOI: 10.11772/j.issn.1001-9081.2023111690
• Multimedia computing and computer simulation • Previous Articles Next Articles
Yongjiang LIU1,2, Bin CHEN2,3,4()
Received:
2023-12-08
Revised:
2024-03-01
Accepted:
2024-03-07
Online:
2024-03-12
Published:
2024-11-10
Contact:
Bin CHEN
About author:
LIU Yongjiang, born in 1996, M. S. candidate. His research interests include object detection, anomaly detection.
通讯作者:
陈斌
作者简介:
刘永江(1996—),男,江西九江人,硕士研究生,主要研究方向:目标检测、异常检测
CLC Number:
Yongjiang LIU, Bin CHEN. Pixel-level unsupervised industrial anomaly detection based on multi-scale memory bank[J]. Journal of Computer Applications, 2024, 44(11): 3587-3594.
刘永江, 陈斌. 基于多尺度记忆库的像素级无监督工业异常检测[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3587-3594.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2023111690
类别 | SPADE[ | CutPaste[ | P-SVDD[ | STFPM[ | PaDiM[ | EfficientAD[ | MemAD |
---|---|---|---|---|---|---|---|
均值 | 85.1 | 92.2 | 96.3 | 90.0 | 95.3 | 97.7 | 98.0 |
bottle | 97.2 | 98.6 | 98.3 | 97.9 | 99.9 | 99.1 | 100.0 |
capsule | 89.7 | 76.7 | 96.2 | 75.9 | 92.7 | 95.7 | 96.4 |
carpet | 92.8 | 92.9 | 93.1 | 95.4 | 99.5 | 97.2 | 87.4 |
grid | 47.3 | 94.6 | 99.9 | 98.2 | 94.2 | 99.8 | 100.0 |
hazelnut | 88.1 | 92.0 | 97.3 | 99.9 | 96.4 | 94.8 | 99.4 |
leather | 95.4 | 90.9 | 100.0 | 98.9 | 100.0 | 100.0 | 100.0 |
metal nut | 71.0 | 94.0 | 99.3 | 95.6 | 98.9 | 98.9 | 100.0 |
pill | 80.3 | 86.1 | 92.4 | 70.5 | 93.9 | 92.6 | 94.8 |
screw | 66.7 | 81.3 | 86.3 | 83.5 | 84.5 | 97.5 | 100.0 |
tile | 96.5 | 97.8 | 93.4 | 94.9 | 97.4 | 99.9 | 100.0 |
toothbrush | 88.9 | 100.0 | 98.3 | 99.7 | 94.2 | 100.0 | 100.0 |
wood | 95.9 | 96.5 | 98.6 | 96.1 | 99.3 | 98.4 | 100.0 |
zipper | 96.6 | 97.9 | 99.4 | 64.5 | 88.2 | 97.1 | 96.5 |
Tab. 1 Image-level AUCs of different methods on MVTec AD dataset
类别 | SPADE[ | CutPaste[ | P-SVDD[ | STFPM[ | PaDiM[ | EfficientAD[ | MemAD |
---|---|---|---|---|---|---|---|
均值 | 85.1 | 92.2 | 96.3 | 90.0 | 95.3 | 97.7 | 98.0 |
bottle | 97.2 | 98.6 | 98.3 | 97.9 | 99.9 | 99.1 | 100.0 |
capsule | 89.7 | 76.7 | 96.2 | 75.9 | 92.7 | 95.7 | 96.4 |
carpet | 92.8 | 92.9 | 93.1 | 95.4 | 99.5 | 97.2 | 87.4 |
grid | 47.3 | 94.6 | 99.9 | 98.2 | 94.2 | 99.8 | 100.0 |
hazelnut | 88.1 | 92.0 | 97.3 | 99.9 | 96.4 | 94.8 | 99.4 |
leather | 95.4 | 90.9 | 100.0 | 98.9 | 100.0 | 100.0 | 100.0 |
metal nut | 71.0 | 94.0 | 99.3 | 95.6 | 98.9 | 98.9 | 100.0 |
pill | 80.3 | 86.1 | 92.4 | 70.5 | 93.9 | 92.6 | 94.8 |
screw | 66.7 | 81.3 | 86.3 | 83.5 | 84.5 | 97.5 | 100.0 |
tile | 96.5 | 97.8 | 93.4 | 94.9 | 97.4 | 99.9 | 100.0 |
toothbrush | 88.9 | 100.0 | 98.3 | 99.7 | 94.2 | 100.0 | 100.0 |
wood | 95.9 | 96.5 | 98.6 | 96.1 | 99.3 | 98.4 | 100.0 |
zipper | 96.6 | 97.9 | 99.4 | 64.5 | 88.2 | 97.1 | 96.5 |
类别 | SPADE[ | CutPaste[ | P-SVDD[ | STFPM[ | PaDiM[ | EfficientAD[ | MemAD |
---|---|---|---|---|---|---|---|
均值 | 95.8 | 95.5 | 96.6 | 96.4 | 96.8 | 95.5 | 97.4 |
bottle | 98.4 | 98.1 | 97.6 | 97.1 | 98.3 | 97.6 | 98.8 |
capsule | 99.0 | 95.8 | 97.4 | 96.2 | 98.4 | 95.7 | 97.4 |
carpet | 97.5 | 92.6 | 98.3 | 98.6 | 98.4 | 94.8 | 96.9 |
grid | 93.7 | 96.2 | 97.5 | 98.8 | 91.8 | 93.7 | 99.2 |
hazelnut | 99.1 | 97.5 | 97.3 | 98.1 | 97.8 | 97.7 | 98.2 |
leather | 97.6 | 97.4 | 99.5 | 99.1 | 99.4 | 97.6 | 96.7 |
metal nut | 98.1 | 98.0 | 93.1 | 94.2 | 97.0 | 98.4 | 99.0 |
pill | 96.5 | 95.1 | 95.7 | 87.8 | 95.7 | 97.8 | 97.7 |
screw | 98.9 | 95.7 | 96.7 | 98.3 | 97.8 | 98.6 | 97.0 |
tile | 87.4 | 91.4 | 90.5 | 94.6 | 93.4 | 90.6 | 99.2 |
toothbrush | 97.9 | 98.1 | 98.1 | 98.3 | 98.8 | 96.4 | 97.6 |
wood | 85.5 | 90.8 | 95.5 | 94.9 | 94.7 | 86.7 | 98.9 |
zipper | 96.5 | 95.1 | 99.3 | 97.2 | 97.9 | 96.0 | 90.8 |
Tab. 2 Pixel-level AUCs of different methods on MVTec AD dataset
类别 | SPADE[ | CutPaste[ | P-SVDD[ | STFPM[ | PaDiM[ | EfficientAD[ | MemAD |
---|---|---|---|---|---|---|---|
均值 | 95.8 | 95.5 | 96.6 | 96.4 | 96.8 | 95.5 | 97.4 |
bottle | 98.4 | 98.1 | 97.6 | 97.1 | 98.3 | 97.6 | 98.8 |
capsule | 99.0 | 95.8 | 97.4 | 96.2 | 98.4 | 95.7 | 97.4 |
carpet | 97.5 | 92.6 | 98.3 | 98.6 | 98.4 | 94.8 | 96.9 |
grid | 93.7 | 96.2 | 97.5 | 98.8 | 91.8 | 93.7 | 99.2 |
hazelnut | 99.1 | 97.5 | 97.3 | 98.1 | 97.8 | 97.7 | 98.2 |
leather | 97.6 | 97.4 | 99.5 | 99.1 | 99.4 | 97.6 | 96.7 |
metal nut | 98.1 | 98.0 | 93.1 | 94.2 | 97.0 | 98.4 | 99.0 |
pill | 96.5 | 95.1 | 95.7 | 87.8 | 95.7 | 97.8 | 97.7 |
screw | 98.9 | 95.7 | 96.7 | 98.3 | 97.8 | 98.6 | 97.0 |
tile | 87.4 | 91.4 | 90.5 | 94.6 | 93.4 | 90.6 | 99.2 |
toothbrush | 97.9 | 98.1 | 98.1 | 98.3 | 98.8 | 96.4 | 97.6 |
wood | 85.5 | 90.8 | 95.5 | 94.9 | 94.7 | 86.7 | 98.9 |
zipper | 96.5 | 95.1 | 99.3 | 97.2 | 97.9 | 96.0 | 90.8 |
stage1 | stage2 | stage3 | AUC | |
---|---|---|---|---|
图像级 | 像素级 | |||
√ | 86.1 | 89.5 | ||
√ | 90.9 | 86.2 | ||
√ | 91.9 | 83.4 | ||
√ | √ | 96.5 | 97.0 | |
√ | √ | 97.1 | 96.6 | |
√ | √ | 97.4 | 94.3 | |
√ | √ | √ | 98.0 | 97.4 |
Tab.3 AUCs of ResNet18 with different stage feature combinations
stage1 | stage2 | stage3 | AUC | |
---|---|---|---|---|
图像级 | 像素级 | |||
√ | 86.1 | 89.5 | ||
√ | 90.9 | 86.2 | ||
√ | 91.9 | 83.4 | ||
√ | √ | 96.5 | 97.0 | |
√ | √ | 97.1 | 96.6 | |
√ | √ | 97.4 | 94.3 | |
√ | √ | √ | 98.0 | 97.4 |
1 | BERGMANN P, LÖWE S, FAUSER M, et al. Improving unsupervised defect segmentation by applying structural similarity to autoencoders[EB/OL]. (2019-02-01) [2023-06-13].. |
2 | TANG T W, KUO W H, LAN J H, et al. Anomaly detection neural network with dual auto-encoders GAN and its industrial inspection applications[J]. Sensors, 2020, 20(12): No.3336. |
3 | AKCAY S, ATAPOUR-ABARGHOUEI A, BRECKON T P. GANomaly: semi-supervised anomaly detection via adversarial training[C]// Proceedings of the 2018 Asian Conference on Computer Vision, LNCS 11363. Cham: Springer, 2019: 622-637. |
4 | SCHLEGL T, SEEBÖCK P, WALDSTEIN S M, et al. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery[C]// Proceedings of the 2017 International Conference on Information Processing in Medical Imaging, LNCS 10265. Cham: Springer, 2017: 146-157. |
5 | ZENATI H, FOO C S, LECOUAT B, et al. Efficient GAN-based anomaly detection[EB/OL]. [2023-06-12].. |
6 | WHEELER B J, KARIMI H A. A semantically driven self-supervised algorithm for detecting anomalies in image sets[J]. Computer Vision and Image Understanding, 2021, 213: No.103279. |
7 | CHEN L C, PAPANDREOU G, KOKKINOS I, et al. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 834-848. |
8 | ROTH K, PEMULA L, ZEPEDA J, et al. Towards total recall in industrial anomaly detection[C]// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 14298-14308. |
9 | COHEN N, HOSHEN Y. Sub-image anomaly detection with deep pyramid correspondences[EB/OL]. [2023-09-10].. |
10 | DEFARD T, SETKOV A, LOESCH A, et al. PaDiM: a patch distribution modeling framework for anomaly detection and localization[C]// Proceedings of the 2021 International Conference on Pattern Recognition, LNCS 12664. Cham: Springer, 2021: 475-489. |
11 | HYUN J, KIM S, JEON G, et al. ReConPatch: contrastive patch representation learning for industrial anomaly detection[C]// Proceedings of the 2024 IEEE/CVF Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2024: 2041-2050. |
12 | 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. Piscataway: IEEE, 2019: 9584-9592. |
13 | ZAVRTANIK V, KRISTAN M, SKOČAJ D. DRÆM — a discriminatively trained reconstruction embedding for surface anomaly detection[C]// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 8310-8319. |
14 | 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. Piscataway: IEEE, 2021: 9659-9669. |
15 | SONG J W, KONG K, PARK Y I, et al. AnoSeg: anomaly segmentation network using self-supervised learning[EB/OL]. [2023-08-10].. |
16 | LIU Z, ZHOU Y, XU Y, et al. SimpleNet: a simple network for image anomaly detection and localization[C]// Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 20402-20411. |
17 | YANG M, WU P, FENG H. MemSeg: a semi-supervised method for image surface defect detection using differences and commonalities[J]. Engineering Applications of Artificial Intelligence, 2023, 119: No.105835. |
18 | DENG J, DONG W, SOCHER R, et al. ImageNet: a large-scale hierarchical image database[C]// Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2009: 248-255. |
19 | HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 770-778. |
20 | SINHA S, ZHANG H, GOYAL A, et al. Small-GAN: speeding up GAN training using core-sets[C]// Proceedings of the 37th International Conference on Machine Learning. New York: JMLR.org, 2020: 9005-9015. |
21 | PERLIN K. An image synthesizer[J]. ACM SIGGRAPH Computer Graphics, 1985, 19(3): 287-296. |
22 | ZHAO R, QIAN B, ZHANG X, et al. Rethinking Dice loss for medical image segmentation[C]// Proceedings of the 2020 IEEE International Conference on Data Mining. Piscataway: IEEE, 2020: 851-860. |
23 | CIMPOI M, MAJI S, KOKKINOS I, et al. Describing textures in the wild[C]// Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2014: 3606-3613. |
24 | FU H, CHENG J, XU Y, et al. Joint optic disc and cup segmentation based on multi-label deep network and polar transformation[J]. IEEE Transactions on Medical Imaging, 2018, 37(7): 1597-1605. |
25 | RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]// Proceedings of the 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 9351. Cham: Springer, 2015: 234-241. |
26 | YAO H, ZHU D L, JIANG B, et al. Negative log likelihood ratio loss for deep neural network classification[C]// Proceedings of the 2019 Future Technologies Conference, AISC 1069. Cham: Springer, 2020: 276-282. |
27 | YI J, YOON S. Patch SVDD: patch-level SVDD for anomaly detection and segmentation[C]// Proceedings of the 2020 Asian Conference on Computer Vision, LNCS 12627. Cham: Springer, 2021: 375-390. |
28 | WANG G, HAN S, DING E, et al. Student-teacher feature pyramid matching for anomaly detection[C]// Proceedings of the 2021 British Machine Vision Conference. Durham: BMVA Press, 2021: No.1273. |
29 | BATZNER K, HECKLER L, KÖNIG R. EfficientAD: accurate visual anomaly detection at millisecond-level latencies[C]// Proceedings of the 2024 IEEE/CVF Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2022: 127-137. |
[1] | Yexin PAN, Zhe YANG. Optimization model for small object detection based on multi-level feature bidirectional fusion [J]. Journal of Computer Applications, 2024, 44(9): 2871-2877. |
[2] | Shuai FU, Xiaoying GUO, Ruyi BAI, Tao YAN, Bin CHEN. Age estimation method combining improved CloFormer model and ordinal regression [J]. Journal of Computer Applications, 2024, 44(8): 2372-2380. |
[3] | Sailong SHI, Zhiwen FANG. Gaze estimation model based on multi-scale aggregation and shared attention [J]. Journal of Computer Applications, 2024, 44(7): 2047-2054. |
[4] | Ziwen SUN, Lizhi QIAN, Chuandong YANG, Yibo GAO, Qingyang LU, Guanglin YUAN. Survey of visual object tracking methods based on Transformer [J]. Journal of Computer Applications, 2024, 44(5): 1644-1654. |
[5] | Guijin HAN, Xinyuan ZHANG, Wentao ZHANG, Ya HUANG. Self-supervised image registration algorithm based on multi-feature fusion [J]. Journal of Computer Applications, 2024, 44(5): 1597-1604. |
[6] | Pengfei ZHANG, Litao HAN, Hengjian FENG, Hongmei LI. Point cloud semantic segmentation based on attention mechanism and global feature optimization [J]. Journal of Computer Applications, 2024, 44(4): 1086-1092. |
[7] | Boyue WANG, Yingxiang LI, Jiandan ZHONG. Segmentation network for day and night ground-based cloud images based on improved Res-UNet [J]. Journal of Computer Applications, 2024, 44(4): 1310-1316. |
[8] | Wei LI, Ling CHEN, Xiuyuan XU, Min ZHU, Jixiang GUO, Kai ZHOU, Hao NIU, Yuchen ZHANG, Shanye YI, Yi ZHANG, Fengming LUO. Interstitial lung disease segmentation algorithm based on multi-task learning [J]. Journal of Computer Applications, 2024, 44(4): 1285-1293. |
[9] | Ning WU, Yangyang LUO, Huajie XU. Semantic segmentation method for remote sensing images based on multi-scale feature fusion [J]. Journal of Computer Applications, 2024, 44(3): 737-744. |
[10] | Yudong PANG, Zhixing LI, Weijie LIU, Tianhao LI, Ningning WANG. Small target detection model in overlooking scenes on tower cranes based on improved real-time detection Transformer [J]. Journal of Computer Applications, 2024, 44(12): 3922-3929. |
[11] | Ziyi LI, Tingting QU, Qianpeng CHONG, Jindong XU. Remote sensing image segmentation network based on fuzzy multiscale features [J]. Journal of Computer Applications, 2024, 44(11): 3581-3586. |
[12] | Wenze CHAI, Jing FAN, Shukui SUN, Yiming LIANG, Jingfeng LIU. Overview of deep metric learning [J]. Journal of Computer Applications, 2024, 44(10): 2995-3010. |
[13] | Qiumei ZHENG, Weiwei NIU, Fenghua WANG, Dan ZHAO. Dual-branch real-time semantic segmentation network based on detail enhancement [J]. Journal of Computer Applications, 2024, 44(10): 3058-3066. |
[14] | Di ZHOU, Zili ZHANG, Jia CHEN, Xinrong HU, Ruhan HE, Jun ZHANG. Stomach cancer image segmentation method based on EfficientNetV2 and object-contextual representation [J]. Journal of Computer Applications, 2023, 43(9): 2955-2962. |
[15] | Yi WANG, Jie XIE, Jia CHENG, Liwei DOU. Review of object pose estimation in RGB images based on deep learning [J]. Journal of Computer Applications, 2023, 43(8): 2546-2555. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||