Achieving Rotational Invariance with Bessel-Convolutional Neural Networks

Résultats de recherche: Contribution dans un livre/un catalogue/un rapport/dans les actes d'une conférenceArticle dans les actes d'une conférence/un colloque

3 Téléchargements (Pure)

Résumé

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.
langue originaleAnglais
titre35th Conference on Neural Information Processing Systems
Sous-titreNeurIPS 2021
Nombre de pages12
Etat de la publicationPublié - 2021
Evénement35th Conference on Neural Information Processing Systems -
Durée: 6 déc. 202114 déc. 2021
Numéro de conférence: 35

Une conférence

Une conférence35th Conference on Neural Information Processing Systems
Titre abrégéNeurIPS 2021
période6/12/2114/12/21

Empreinte digitale

Examiner les sujets de recherche de « Achieving Rotational Invariance with Bessel-Convolutional Neural Networks ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation