Achieving Rotational Invariance with Bessel-Convolutional Neural Networks

Valentin Delchevalerie; Adrien Bibal; Benoît Frénay; Alexandre Mayer

Achieving Rotational Invariance with Bessel-Convolutional Neural Networks

Valentin Delchevalerie, Adrien Bibal, Benoît Frénay, Alexandre Mayer

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

32 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 originale	Anglais
titre	35th Conference on Neural Information Processing Systems
Sous-titre	NeurIPS 2021
Nombre de pages	12
Volume	34
ISBN (Electronique)	9781713845393
Etat de la publication	Publié - 2021
Evénement	35th Conference on Neural Information Processing Systems - Durée: 6 déc. 2021 → 14 déc. 2021 Numéro de conférence: 35

Une conférence

Une conférence	35th Conference on Neural Information Processing Systems
Titre abrégé	NeurIPS 2021
période	6/12/21 → 14/12/21

Accès au document

NeurIPS_Bessel_CNN

https://proceedings.neurips.cc/paper/2021/hash/f18224a1adfb7b3dbff668c9b655a35a-Abstract.htmlLicense: Non spécifié

CÉCI – Consortium des Équipements de Calcul Intensif
Champagne, B., Lazzaroni, R., Geuzaine , C., Chatelain, P. & Knaepen, B.
1/01/18 → 31/12/22
Projet: Recherche

Plateforme Technologique Calcul Intensif
Benoît Champagne (!!Manager)
Plateforme technologique Calcul intensif
Equipement/installations: Plateforme technolgique

Contient cette citation

@inproceedings{671d42c6f9b447ce8012024e9b0ab4ac,

title = "Achieving Rotational Invariance with Bessel-Convolutional Neural Networks",

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.",

keywords = "machine learning, computer vision, neural networks, image classification, rotational invariance, Bessel-CNN",

author = "Valentin Delchevalerie and Adrien Bibal and Beno{\^i}t Fr{\'e}nay and Alexandre Mayer",

year = "2021",

language = "English",

volume = "34",

booktitle = "35th Conference on Neural Information Processing Systems",

note = "35th Conference on Neural Information Processing Systems ; Conference date: 06-12-2021 Through 14-12-2021",

}

Delchevalerie, V , Bibal, A , Frénay, B & Mayer, A 2021, Achieving Rotational Invariance with Bessel-Convolutional Neural Networks. Dans 35th Conference on Neural Information Processing Systems: NeurIPS 2021. VOL. 34, 35th Conference on Neural Information Processing Systems, 6/12/21. <https://proceedings.neurips.cc/paper/2021/hash/f18224a1adfb7b3dbff668c9b655a35a-Abstract.html>

Achieving Rotational Invariance with Bessel-Convolutional Neural Networks. / Delchevalerie, Valentin ; Bibal, Adrien ; Frénay, Benoît et al.
35th Conference on Neural Information Processing Systems: NeurIPS 2021. Vol 34 2021.

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

TY - GEN

T1 - Achieving Rotational Invariance with Bessel-Convolutional Neural Networks

AU - Delchevalerie, Valentin

AU - Bibal, Adrien

AU - Frénay, Benoît

AU - Mayer, Alexandre

N1 - Conference code: 35

PY - 2021

Y1 - 2021

N2 - 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.

AB - 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.

KW - machine learning

KW - computer vision

KW - neural networks

KW - image classification

KW - rotational invariance

KW - Bessel-CNN

M3 - Conference contribution

VL - 34

BT - 35th Conference on Neural Information Processing Systems

T2 - 35th Conference on Neural Information Processing Systems

Y2 - 6 December 2021 through 14 December 2021

ER -

Achieving Rotational Invariance with Bessel-Convolutional Neural Networks

Résumé

Une conférence

Accès au document

Empreinte digitale

Projets

CÉCI – Consortium des Équipements de Calcul Intensif

Équipement

Plateforme Technologique Calcul Intensif

Contient cette citation