From Three to Two Dimensions: 2D Quaternion Convolutions for 3D Images

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

Résumé

In fields like biomedical imaging, it is common to manage 3D images instead of 2D ones (CT-scans, MRI, 3D-ultrasound, etc.). Although 3D-Convolutional Neural Networks (CNNs) are generally more powerful compared to their 2D counterparts for such applications, it also comes at the cost of an increase in computational resources (both in time and memory). In this work, we present a new way to build 2D representations of 3D images while minimizing the information loss by leveraging quaternions. Those quaternion CNNs are able to offer competitive performance while significantly reducing computational complexity.
langue originaleAnglais
titreESANN 2024 Proceedings - The 32th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Etat de la publicationPublié - 2024

Série de publications

NomESANN 2024 Proceedings

Empreinte digitale

Examiner les sujets de recherche de « From Three to Two Dimensions: 2D Quaternion Convolutions for 3D Images ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation