Knowledge Distillation Anomaly Detection with Multi-Scale Feature Fusion

被引：0

作者：

Yadang C. ^{[1
,2
]}

Liuren C. ^{[1
,2
]}

Wenbin Y. ^{[1
]}

Jiale Z. ^{[1
]}

机构：

[1] School of Computer Science, Nanjing University of Information Science and Technology, Nanjing

[2] Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science and Technology, Nanjing

来源：

Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics | 2022年 / 34卷 / 10期

关键词：

anomaly detection; feature fusion; knowledge distillation; one-class-classification problem;

D O I：

10.3724/SP.J.1089.2022.19730

中图分类号：

学科分类号：

摘要：

To enhance the generalization of anomaly detection, this paper proposes a multi-scale detection method based on knowledge distillation. During training, the well-pretrained teacher network is used to teach the student network to learn the feature of normal samples. During testing, the teacher network can still represent anomaly well due to its strong generalization, while the student network cannot. The difference between them makes the detection task available. Furthermore, a mid-level feature pyramid structure is adopted to enhance the ability for handling the anomaly with different size, and a feature reconstruction modular is also employed to enlarge the difference between teacher and student network for an anomaly. The method achieves 97.8% and 97.7% AUC score on pixel and image level respectively, evaluated on the public benchmark-MVTecAD. © 2022 Institute of Computing Technology. All rights reserved.

引用

页码：1542 / 1549

页数：7

共 24 条

[1]

Bergmann P, Fauser M, Sattlegger D, Et al., MVTecAD — a comprehensive real-world dataset for unsupervised anomaly detection, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9584-9592, (2019)

[2]

Li Z, Wang C, Han M, Et al., Thoracic disease identification and localization with limited supervision, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8290-8299, (2018)

[3]

Ruff L, Vandermeulen R A, Gornitz N, Et al., Deep one-class classification, Proceedings of the 35th International Conference on Machine Learning, pp. 4393-4402, (2018)

[4]

Goyal S, Raghunathan A, Jain M, Et al., DROCC: deep robust one-class classification, Proceedings of International Conference on Machine Learning, pp. 3711-3721, (2020)

[5]

Bergmann P, Lowe S, Fauser M, Et al., Improving unsupervised defect segmentation by applying structural similarity to autoencoders

[6]

Chen Yadang, Hao Chuanyan, Video object segmentation based on dynamic bilateral grid, Journal of Computer-Aided Design & Computer Graphics, 30, 11, pp. 2101-2107, (2018)

[7]

Defard T, Setkov A, Loesch A, Et al., PaDiM: a patch distribution modeling framework for anomaly detection and localization[C], Proceedings of International Conference on Pattern Recognition, pp. 475-489, (2021)

[8]

Bergmann P, Fauser M, Sattlegger D, Et al., Uninformed students: student-teacher anomaly detection with discriminative latent embeddings, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4182-4191, (2020)

[9]

Romero A, Ballas N, Kahou S E, Et al., Fitnets: hints for thin deep nets

[10]

Salehi M, Sadjadi N, Baselizadeh S, Et al., Multiresolution knowledge distillation for anomaly detection, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14897-14907, (2021)

← 1 2 3 →