Abstract

For many applications in image analysis, learning models that are invariant to translations and rotations is paramount. This is the case, for example, in medical imaging where the objects of interest can appear at arbitrary positions, with arbitrary orientations. As of today, Convolutional Neural Networks (CNN) are one of the most powerful tools for image analysis. They achieve, thanks to convolutions, an invariance with respect to translations. In this work, we present a new type of convolutional layer that takes advantage of Bessel functions, well known in physics, to build Bessel-CNNs (B-CNNs) that are invariant to all the continuous set of possible rotation angles by design.
Original languageEnglish
Title of host publication35th Conference on Neural Information Processing Systems
Subtitle of host publicationNeurIPS 2021
Number of pages12
Publication statusPublished - 2021
Event35th Conference on Neural Information Processing Systems -
Duration: 6 Dec 202114 Dec 2021
Conference number: 35

Conference

Conference35th Conference on Neural Information Processing Systems
Abbreviated titleNeurIPS 2021
Period6/12/2114/12/21

Keywords

  • machine learning
  • computer vision
  • neural networks
  • image classification
  • rotational invariance
  • Bessel-CNN

Fingerprint

Dive into the research topics of 'Achieving Rotational Invariance with Bessel-Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this