Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
Published in:
Using Assurance Cases to Prevent Malicious Behaviour from Targeting Safety Vulnerabilities Read chapter Read first chapter

2023 | OriginalPaper | Chapter

Contextualised Out-of-Distribution Detection Using Pattern Identification

Authors : Romain Xu-Darme, Julien Girard-Satabin, Darryl Hond, Gabriele Incorvaia, Zakaria Chihani

Published in: Computer Safety, Reliability, and Security. SAFECOMP 2023 Workshops

Publisher: Springer Nature Switzerland

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

In this work, we propose CODE, an extension of existing work from the field of explainable AI that identifies class-specific recurring patterns to build a robust Out-of-Distribution (OoD) detection method for visual classifiers. CODE does not require any classifier retraining and is OoD-agnostic, i.e., tuned directly to the training dataset. Crucially, pattern identification allows us to provide images from the In-Distribution (ID) dataset as reference data to provide additional context to the confidence scores. In addition, we introduce a new benchmark based on perturbations of the ID dataset that provides a known and quantifiable measure of the discrepancy between the ID and OoD datasets serving as a reference value for the comparison between OoD detection methods.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

inform now
previous chapter Can Large Language Models Assist in Hazard Analysis?
Footnotes
1
Class-agnostic methods simply ignore the image label/prediction.
 
2
Although good approximations of the normal CDF using sigmoids exist [3].
 
Literature
1.
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR 2009, pp. 248–255 (2009)
2.
Deng, L.: The MNIST database of handwritten digit images for machine learning research. IEEE Signal Process. Mag. 29(6), 141–142 (2012)CrossRef
3.
Eidous, O.M., Al-Rawash, M.: Approximations for standard normal distribution function and its invertible. ArXiv (2022)
4.
Han, J., Yao, X., Cheng, G., Feng, X., Xu, D.: P-CNN: part-based convolutional neural networks for fine-grained visual categorization. IEEE Trans. Pattern Anal. Mach. Intell. 44(2), 579–590 (2022)CrossRef
5.
Hein, M., Andriushchenko, M., Bitterwolf, J.: Why RELU networks yield high-confidence predictions far away from the training data and how to mitigate the problem? In: CVPR 2019, pp. 41–50 (2019)
6.
Hendrycks, D., Basart, S., Mazeika, M., Mostajabi, M., Steinhardt, J., Song, D.X.: Scaling out-of-distribution detection for real-world settings. In: ICML 2022 (2022)
7.
Hendrycks, D., Dietterich, T.G.: Benchmarking neural network robustness to common corruptions and perturbations. ArXiv (2018)
8.
Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. In: ICLR 2017 (2017)
9.
Hond, D., Asgari, H., Jeffery, D., Newman, M.: An integrated process for verifying deep learning classifiers using dataset dissimilarity measures. Int. J. Artif. Intell. Mach. Learn. 11(2), 1–21 (2021)
10.
Huang, R., Geng, A., Li, Y.: On the importance of gradients for detecting distributional shifts in the wild. In: NeurIPS 2021 (2021)
11.
Krizhevsky, A.: Learning multiple layers of features from tiny images. Technical report (2009)
12.
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)
13.
Lee, K., Lee, K., Lee, H., Shin, J.: A simple unified framework for detecting out-of-distribution samples and adversarial attacks. In: NeurIPS (2018)
14.
Li, H., Zhang, X., Tian, Q., Xiong, H.: Attribute mix: semantic data augmentation for fine grained recognition. In: 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP), pp. 243–246 (2020)
15.
Liang, S., Li, Y., Srikant, R.: Enhancing the reliability of out-of-distribution image detection in neural networks. In: ICLR 2018 (2018)
16.
Liu, W., Wang, X., Owens, J., Li, Y.: Energy-based out-of-distribution detection. In: NeurIPS 2020, pp. 21464–21475 (2020)
17.
Mukhoti, J., et al.: Raising the bar on the evaluation of out-of-distribution detection. ArXiv (2022)
18.
Sastry, C.S., Oore, S.: Detecting out-of-distribution examples with gram matrices. In: ICML (2020)
19.
Smilkov, D., Thorat, N., Kim, B., Viégas, F.B., Wattenberg, M.: SmoothGrad: removing noise by adding noise. ArXiv (2017)
20.
Sun, Y., Guo, C., Li, Y.: ReAct: out-of-distribution detection with rectified activations. In: NeurIPS 2021 (2021)
21.
Sun, Y., Li, Y.: DICE: leveraging sparsification for out-of-distribution detection. In: ICCV 2021 (2021)
22.
Sun, Y., Ming, Y., Zhu, X., Li, Y.: Out-of-distribution detection with deep nearest neighbors. In: ICML 2022 (2022)
23.
Szegedy, C., et al.: Intriguing properties of neural networks. In: ICLR 2014 (2014)
24.
Wang, H., Li, Z., Feng, L., Zhang, W.: ViM: out-of-distribution with virtual-logit matching. In: CVPR 2022 (2022)
25.
26.
Xu-Darme, R., Quénot, G., Chihani, Z., Rousset, M.C.: PARTICUL: part identification with confidence measure using unsupervised learning. In: XAIE: 2nd Workshop on Explainable and Ethical AI - ICPR 2022 (2022)
27.
Yang, J., et al.: OpenOOD: benchmarking generalized out-of-distribution detection. NeurIPS 2022 - Datasets and Benchmarks Track (2022)
28.
Zhao, X., et al.: Recognizing part attributes with insufficient data. In: ICCV 2019 (2019)
29.
Zheng, H., Fu, J., Mei, T., Luo, J.: Learning multi-attention convolutional neural network for fine-grained image recognition. In: ICCV 2017 (2017)
Metadata
Title
Contextualised Out-of-Distribution Detection Using Pattern Identification
Authors
Romain Xu-Darme
Julien Girard-Satabin
Darryl Hond
Gabriele Incorvaia
Zakaria Chihani
Copyright Year
2023
Book
Computer Safety, Reliability, and Security. SAFECOMP 2023 Workshops

Print ISBN: 978-3-031-40952-3

Electronic ISBN: 978-3-031-40953-0

Copyright Year: 2023

DOI
https://doi.org/10.1007/978-3-031-40953-0_36

Premium Partner

    Image Credits