Skip to main content
SpringerLink
Log in

A weakly supervised anomaly detection method based on deep anomaly scoring network

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

Recently most anomaly detection methods mainly use normal samples or unlabeled data for training. Due to the lack of prior anomaly knowledge, normal samples with noisy data are easy to be misjudged as anomalies. Therefore, this paper proposes a weakly supervised anomaly detection model based on a deep anomaly scoring network. In this model, ResNet is used as a feature extraction network, and the Res2Net module is added to ResNet, which extracts multi-scale features at a fine-grained level to improve the multi-scale representation ability of the network. At the same time, efficient channel attention is introduced to enhance feature extraction performance by allocating the attention to feature channels. In addition, the anomaly score network calculates the anomaly score directly according to the extracted feature representation and optimizes the anomaly score in an end-to-end way. Comprehensive experiments on the challenging MVTec AD, KolektorSDD and ELPV datasets show that compared with the current advanced anomaly detection methods, our model achieves better results in anomaly detection and location, and has better robustness.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Data availability

Data is publicly available.

References

  1. Chandola, V., Banerjee, A., Kumar, V.: Anomaly detection: a survey. ACM Comput. Surv. 41(3), 1–58 (2009)

    Article  Google Scholar 

  2. Ruff, L., Kauffmann, J.R., Vandermeulen, R.A.: A unifying review of deep and shallow anomaly detection. Proc. IEEE 109(5), 756–795 (2021)

    Article  Google Scholar 

  3. Asgari, T.S., Abhishek, K., Cohen, J.P.: Deep semantic segmentation of natural and medical images: a review. Artif. Intell. Rev. 54(1), 137–178 (2021)

    Article  Google Scholar 

  4. Georgescu, M.I., Barbalau, A., Ionescu, R.T.: Anomaly detection in video via self-supervised and multi-task learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12742–12752 (2021)

  5. Xie, X., Huang, Y.H., Ning, W.Y.: RDAD: a reconstructive and discriminative anomaly detection model based on transformer. Int. J. Intell. Syst. 37(11), 8928–8946 (2022)

    Article  Google Scholar 

  6. Xie, X., Xu, L., Li, X.L.: A high-effective multitask surface defect detection method based on CBAM and atrous convolution. J. Adv. Mech. Design Syst. Manuf. 16(6), 12–14 (2022)

    Google Scholar 

  7. Bergman, L., Hoshen, Y.: Classification-based anomaly detection for general data. In: International Conference on Learning Representations (2020)

  8. Perera, P., Patel, V.M.: Learning deep features for one-class classification. IEEE Trans. Image Process. 28(11), 5450–5463 (2019)

    Article  MathSciNet  MATH  Google Scholar 

  9. Ruff, L., Vandermeulen, R.A., Görnitz, N.: Deep one-class classification. In: International Conference on Machine Learning (2018)

  10. Liznerski, P., Ruff, L., Vandermeulen, R.A.: Explainable deep one-class classification. https://arxiv.org/abs/2007.01760v2 (2020)

  11. An, J., Cho, S.: Variational autoencoder based anomaly detection using reconstruction probability. Spec Lect IE 2(1), 1–18 (2015)

    Google Scholar 

  12. Gong, D., Liu, L., Le, V.: Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1705–1714 (2019)

  13. Sheynin, S., Benaim, S., Wolf, L.: A hierarchical transformation-discriminating generative model for few shot anomaly detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8495–8504 (2021)

  14. Zaheer, M.Z., Lee, J., Astrid, M.: Old is gold: Redefining the adversarially learned one-class classifier training paradigm. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14183–14193 (2020)

  15. Salehi, M., Sadjadi, N., Baselizadeh, S.: Multiresolution knowledge distillation for anomaly detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14902–14912 (2021)

  16. Reiss, T., Cohen, N., Bergman, L., Hoshen, Y.: Panda: adapting pretrained features for anomaly detection and segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2806–2814 (2021)

  17. Defard, T., Setkov, A., Loesch, A.: Padim: a patch distribution modeling framework for anomaly detection and localization. In: International Conference on Pattern Recognition, pp. 475–489. Springer, Cham (2021)

  18. Rudolph, M., Wandt, B., Rosenhahn, B.: Same same but differnet: semi-supervised defect detection with normalizing flows. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 1907–1916 (2021)

  19. Kingma, D.P., Dhariwal, P.: Glow: generative flow with invertible 1x1 convolutions. Adv. Neural Inf. Process. Syst. 31 (2018)

  20. He, K., Zhang, X., Ren, S.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

  21. Gao, S.H., Cheng, M.M., Zhao, K.: Res2net: a new multi-scale backbone architecture. IEEE Trans. Pattern Anal. Mach. Intell. 43(2), 652–662 (2019)

    Article  Google Scholar 

  22. Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: ECA-Net: efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11531–11539 (2020)

  23. Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)

  24. Bergmann, P., Fauser, M., Sattlegger, D.: MVTec AD—a comprehensive real-world dataset for unsupervised anomaly detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9592–9600 (2019)

  25. Tabernik, D., Šela, S., Skvarč, J.: Segmentation-based deep-learning approach for surface-defect detection. J. Intell. Manuf. 31(3), 759–776 (2020)

    Article  Google Scholar 

  26. Deitsch, S., Christlein, V., Berger, S.: Automatic classification of defective photovoltaic module cells in electroluminescence images. Sol. Energy 185, 455–468 (2019)

    Article  Google Scholar 

  27. Ruff, L., Vandermeulen, R.A., Grnitz, N.: Deep semi-supervised anomaly detection. In: International Conference on Learning Representations (2019)

  28. Pang, G., Ding, C., Shen, C.: Explainable deep few-shot anomaly detection with deviation networks. https://arxiv.org/abs/2108.00462 (2021)

  29. Paszke, A., Gross, S., Chintala, S.: Automatic differentiation in pytorch. In: Conference and Workshop on Neural Information Processing Systems (2017)

  30. Kingma, D., Ba, J.: Adam: a method for stochastic optimization. Comput Sci (2014)

Download references

Acknowledgements

This paper is supported by the National Natural Science Foundation of China, under Grant No. 62162026, and the Science and Technology Project supported by Education Department of Jiangxi Province, under Grant No. GJJ210611.

Author information

Authors and Affiliations

  1. School of Information Engineering, East China Jiaotong University, Nanchang, 330013, Jiangxi, China

    Xin Xie, Zixi Li, Yuhui Huang & Dengquan Wu

Authors
  1. Xin Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zixi Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yuhui Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Dengquan Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

XX and ZL designed the study, conducted the anomaly detection experiments and wrote the manuscript, and YH and DW provided technical support and assistance with data analysis. All authors reviewed and edited the manuscript.

Corresponding author

Correspondence to Zixi Li.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xie, X., Li, Z., Huang, Y. et al. A weakly supervised anomaly detection method based on deep anomaly scoring network. SIViP 17, 3903–3911 (2023). https://doi.org/10.1007/s11760-023-02619-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-023-02619-7

Keywords

Search

Navigation