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:
Cover of the book

2021 | OriginalPaper | Chapter

Scale-Covariant and Scale-Invariant Gaussian Derivative Networks

Author : Tony Lindeberg

Published in: Scale Space and Variational Methods in Computer Vision

Publisher: Springer International Publishing

Log in

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

search-config
loading …

Abstract

This paper presents a hybrid approach between scale-space theory and deep learning, where a deep learning architecture is constructed by coupling parameterized scale-space operations in cascade. By sharing the learnt parameters between multiple scale channels, and by using the transformation properties of the scale-space primitives under scaling transformations, the resulting network becomes provably scale covariant. By in addition performing max pooling over the multiple scale channels, a resulting network architecture for image classification also becomes provably scale invariant. We investigate the performance of such networks on the MNISTLargeScale dataset, which contains rescaled images from original MNIST over a factor of 4 concerning training data and over a factor of 16 concerning testing data. It is demonstrated that the resulting approach allows for scale generalization, enabling good performance for classifying patterns at scales not present in the training data.

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
next chapter Quantisation Scale-Spaces
Literature
1.
Jansson, Y., Lindeberg, T.: Exploring the ability of CNNs to generalise to previously unseen scales over wide scale ranges. In: International Conference on Pattern Recognition (ICPR 2020), pp. 1181–1188 (2021)
2.
Lindeberg, T.: Provably scale-covariant continuous hierarchical networks based on scale-normalized differential expressions coupled in cascade. J. Math. Imaging Vis. 62, 120–148 (2020)MathSciNetCrossRef
3.
Lindeberg, T.: Feature detection with automatic scale selection. Int. J. Comput. Vis. 30, 77–116 (1998)
4.
Lindeberg, T.: Edge detection and ridge detection with automatic scale selection. Int. J. Comput. Vis. 30, 117–154 (1998)CrossRef
5.
Mikolajczyk, K., Schmid, C.: Scale and affine invariant interest point detectors. Int. J. Comput. Vis. 60, 63–86 (2004)CrossRef
6.
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60, 91–110 (2004)CrossRef
7.
Bay, H., Ess, A., Tuytelaars, T., van Gool, L.: Speeded up robust features (SURF). CVIU 110, 346–359 (2008)
8.
Lindeberg, T.: Image matching using generalized scale-space interest points. J. Math. Imaging Vis. 52, 3–36 (2015)MathSciNetCrossRef
9.
Fawzi, A., Frossard, P.: Manitest: are classifiers really invariant? In: British Machine Vision Conference (BMVC 2015) (2015)
10.
Singh, B., Davis, L.S.: An analysis of scale invariance in object detection – SNIP. In: Proceedings Computer Vision and Pattern Recognition (CVPR 2018), pp. 3578–3587 (2018)
11.
Xu, Y., Xiao, T., Zhang, J., Yang, K., Zhang, Z.: Scale-invariant convolutional neural networks. arXiv preprint arXiv:​1411.​6369 (2014)
12.
Kanazawa, A., Sharma, A., Jacobs, D.W.: Locally scale-invariant convolutional neural networks. arXiv preprint arXiv:​1412.​5104 (2014)
13.
Marcos, D., Kellenberger, B., Lobry, S., Tuia, D.: Scale equivariance in CNNs with vector fields. arXiv preprint arXiv:​1807.​11783 (2018)
14.
Ghosh, R., Gupta, A.K.: Scale steerable filters for locally scale-invariant convolutional neural networks. arXiv preprint arXiv:​1906.​03861 (2019)
15.
Worrall, D., Welling, M.: Deep scale-spaces: equivariance over scale. In: Advances in Neural Information Processing Systems, pp. 7366–7378 (2019)
16.
Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. In: Proceedings of Neural Information Processing Systems (NIPS 2015), pp. 2017–2025 (2015)
17.
Finnveden, L., Jansson, Y., Lindeberg, T.: Understanding when spatial transformer networks do not support invariance, and what to do about it. In: International Conference on Pattern Recognition (ICPR 2020), pp. 3427–3434 (2021)
18.
Roux, N.L., Bengio, Y.: Continuous neural networks. In: Artificial Intelligence and Statistics (AISTATS 2007), vol. 2, pp. 404–411 (2007)
19.
Shocher, A., Feinstein, B., Haim, N., Irani, M.: From discrete to continuous convolution layers. arXiv preprint arXiv:​2006.​11120 (2020)
20.
Iijima, T.: Basic theory on normalization of pattern (in case of typical one-dimensional pattern). Bull. Electrotech. Lab. 26, 368–388 (1962)
21.
22.
Koenderink, J.J., van Doorn, A.J.: Generic neighborhood operators. IEEE-TPAMI 14, 597–605 (1992)CrossRef
23.
Lindeberg, T.: Scale-Space Theory in Computer Vision. Springer, New York (1993). 10.1007/978-1-4757-6465-9
24.
Florack, L.M.J.: Image Structure. Springer, Dordrecht (1997). 10.1007/978-94-015-8845-4
25.
ter Haar Romeny, B.: Front-End Vision and Multi-Scale Image Analysis. Springer, Dordrecht (2003). 10.1007/978-1-4020-8840-7
26.
Lindeberg, T.: Generalized Gaussian scale-space axiomatics comprising linear scale-space, affine scale-space and spatio-temporal scale-space. J. Math. Imaging Vis. 40, 36–81 (2011)MathSciNetCrossRef
27.
28.
Jacobsen, J.J., van Gemert, J., Lou, Z., Smeulders, A.W.M.: Structured receptive fields in CNNs. In: Proceedings of Computer Vision and Pattern Recognition (CVPR 2016), pp. 2610–2619 (2016)
29.
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998)CrossRef
30.
Kingma, P.D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference for Learning Representations (ICLR 2015) (2015)
31.
Lindeberg, T.: Scale-space for discrete signals. IEEE-TPAMI 12, 234–254 (1990)CrossRef
32.
Lindeberg, T.: Discrete derivative approximations with scale-space properties: a basis for low-level feature extraction. J. Math. Imaging Vis. 3, 349–376 (1993)CrossRef
33.
Jansson, Y., Lindeberg, T.: MNISTLargeScaledataset. Zenodo (2020)
34.
35.
Li, Y., Tax, D.M.J., Loog, M.: Scale selection for supervised image segmentation. Image Vis. Comput. 30, 991–1003 (2012)CrossRef
Metadata
Title
Scale-Covariant and Scale-Invariant Gaussian Derivative Networks
Author
Tony Lindeberg
Copyright Year
2021
Book
Scale Space and Variational Methods in Computer Vision

Print ISBN: 978-3-030-75548-5

Electronic ISBN: 978-3-030-75549-2

Copyright Year: 2021

DOI
https://doi.org/10.1007/978-3-030-75549-2_1

Premium Partner

    Image Credits