TY - GEN
T1 - From Three to Two Dimensions: 2D Quaternion Convolutions for 3D Images
AU - Delchevalerie, Valentin
AU - Frénay, Benoît
AU - Mayer, Alexandre
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
M3 - Conference contribution
T3 - ESANN 2024 Proceedings
BT - ESANN 2024 Proceedings - The 32th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
ER -