Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 1.43 MB
Add to list
  1. Search results
  2. Spatial chirp-Z transformer networks

Spatial chirp-Z transformer networks

Jonas Degrave (UGent) , Sander Dieleman (UGent) , Joni Dambre (UGent) and Francis wyffels (UGent)
(2016) European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2016), Proceedings. p.545-550
Author
Organization
Abstract
Convolutional Neural Networks are often used for computer vision solutions, because of their inherent modeling of the translation invariance in images. In this paper, we propose a new module to model rotation and scaling invariances in images. To do this, we rely on the chirp-Z transform to perform the desired translation, rotation and scaling in the frequency domain. This approach has the benefit that it scales well and that it is differentiable because of the computationally cheap sincinterpolation.
Keywords
chirp-z transformation, spatial transformation, machine learning, Neural networks

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.43 MB

Citation

Please use this url to cite or link to this publication:

MLA
Degrave, Jonas, et al. “Spatial Chirp-Z Transformer Networks.” European Symposium on Artificial Neural Networks, Computational  Intelligence and Machine Learning (ESANN 2016), Proceedings, 2016, pp. 545–50.
APA
Degrave, J., Dieleman, S., Dambre, J., & wyffels, F. (2016). Spatial chirp-Z transformer networks. European Symposium on Artificial Neural Networks, Computational  Intelligence and Machine Learning (ESANN 2016), Proceedings, 545–550.
Chicago author-date
Degrave, Jonas, Sander Dieleman, Joni Dambre, and Francis wyffels. 2016. “Spatial Chirp-Z Transformer Networks.” In European Symposium on Artificial Neural Networks, Computational  Intelligence and Machine Learning (ESANN 2016), Proceedings, 545–50.
Chicago author-date (all authors)
Degrave, Jonas, Sander Dieleman, Joni Dambre, and Francis wyffels. 2016. “Spatial Chirp-Z Transformer Networks.” In European Symposium on Artificial Neural Networks, Computational  Intelligence and Machine Learning (ESANN 2016), Proceedings, 545–550.
Vancouver
1.
Degrave J, Dieleman S, Dambre J, wyffels F. Spatial chirp-Z transformer networks. In: European Symposium on Artificial Neural Networks, Computational  Intelligence and Machine Learning (ESANN 2016), Proceedings. 2016. p. 545–50.
IEEE
[1]
J. Degrave, S. Dieleman, J. Dambre, and F. wyffels, “Spatial chirp-Z transformer networks,” in European Symposium on Artificial Neural Networks, Computational  Intelligence and Machine Learning (ESANN 2016), Proceedings, Bruges, Belgium, 2016, pp. 545–550.
@inproceedings{7178424,
  abstract     = {{Convolutional Neural Networks are often used for computer vision solutions, because of their inherent modeling of the translation invariance in images. In this paper, we propose a new module to model rotation and scaling invariances in images. To do this, we rely on the chirp-Z transform to perform the desired translation, rotation and scaling in the frequency domain. This approach has the benefit that it scales well and that it is differentiable because of the computationally cheap sincinterpolation.}},
  author       = {{Degrave, Jonas and Dieleman, Sander and Dambre, Joni and wyffels, Francis}},
  booktitle    = {{European Symposium on Artificial Neural Networks, Computational  Intelligence and Machine Learning (ESANN 2016), Proceedings}},
  isbn         = {{9782875870278}},
  keywords     = {{chirp-z transformation,spatial transformation,machine learning,Neural networks}},
  language     = {{eng}},
  location     = {{Bruges, Belgium}},
  pages        = {{545--550}},
  title        = {{Spatial chirp-Z transformer networks}},
  year         = {{2016}},
}