skip to main content
10.1145/3653644.3653649acmotherconferencesArticle/Chapter ViewAbstractPublication PagesfaimlConference Proceedingsconference-collections
research-article

Siamese Contrastive Reverse Distillation for Industrial Anomaly Localization

Published: 20 September 2024 Publication History

Abstract

The unsupervised anomaly localization based on feature distillation has demonstrated outstanding performance in industrial anomaly localization. It relies on the feature discrepancies between the student network and the teacher network to achieve anomaly localization. In these methods, the student network exclusively learns from the normal features of the teacher network during training, overlooking the explicit constraining of prior anomaly knowledge. This results in uncertainty in the feature discrepancy between the student and teacher for abnormal inputs, leading to a decrease in prediction accuracy. To inject prior anomaly knowledge into the student network during training, this paper proposes Fine-Grained CutPaste (FG-CutPaste) data augmentation strategy and Siamese Contrastive Reverse Distillation Network (SCRD). FG-CutPaste provides pseudo-abnormal samples and corresponding pixel-level pseudo-abnormal labels during the training phase of SCRD. SCRD introduces the Siamese network paradigm along with Contrastive Distillation (CD) loss. The CD loss, utilizing pseudo-abnormal samples and labels, not only reduces the discrepancy of normal features between the student and teacher networks of SCRD but also increases the discrepancy of their abnormal features, achieving explicit constraint on the abnormal features of the student. Experimental results indicate that SCRD achieves outstanding anomaly localization performance, yielding more refined visualizations for anomaly localization.

References

[1]
Bergmann, P., Fauser, M., Sattlegger, D., and Steger, C. (2020). Uninformed students: Student-teacher anomaly detection with discriminative latent embeddings. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 4183-4192.
[2]
Defard, T., Setkov, A., Loesch, A., and Audigier, R. (2021, January). Padim: a patch distribution modeling framework for anomaly detection and localization. In International Conference on Pattern Recognition, pp. 475-489. Cham: Springer International Publishing.
[3]
He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778.
[4]
Deng, H., and Li, X. (2022). Anomaly detection via reverse distillation from one-class embedding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9737-9746.
[5]
Wang, G., Han, S., Ding, E., and Huang, D. (2021). Student-teacher feature pyramid matching for anomaly detection. arXiv preprint arXiv:2103.04257.
[6]
Cao, Y., Wan, Q., Shen, W., and Gao, L. (2022). Informative knowledge distillation for image anomaly segmentation. Knowledge-Based Systems, 248, 108846.
[7]
Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., and Fei-Fei, L. (2009, June). Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pp. 248-255. Ieee.
[8]
Li, C. L., Sohn, K., Yoon, J., and Pfister, T. (2021). Cutpaste: Self-supervised learning for anomaly detection and localization. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 9664-9674.
[9]
Melekhov, I., Kannala, J., and Rahtu, E. (2016, December). Siamese network features for image matching. In 2016 23rd international conference on pattern recognition (ICPR), pp. 378-383. IEEE.
[10]
Zagoruyko, S., and Komodakis, N. (2016). Wide residual networks. arXiv preprint arXiv:1605.07146.

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
FAIML '24: Proceedings of the 2024 3rd International Conference on Frontiers of Artificial Intelligence and Machine Learning
April 2024
379 pages
ISBN:9798400709777
DOI:10.1145/3653644
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 20 September 2024

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. anomaly localization
  2. contrastive learning
  3. knowledge distillation

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

FAIML 2024

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 10
    Total Downloads
  • Downloads (Last 12 months)10
  • Downloads (Last 6 weeks)1
Reflects downloads up to 13 Feb 2025

Other Metrics

Citations

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media