% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Zhao:283020,
author = {Zhao, Wenzhao and Albert, Steffen and Wichtmann, Barbara D.
and Schmitt, Angelika and Attenberger, Ulrike and Zöllner,
Frank G. and Hesser, Jürgen},
title = {{E}fficient 3{D} affinely equivariant {CNN}s with adaptive
fusion of augmented spherical {F}ourier–{B}essel bases},
journal = {Information fusion},
volume = {127},
issn = {1566-2535},
address = {Amsterdam [u.a.]},
publisher = {Elsevier Science},
reportid = {DZNE-2025-01432},
pages = {103823},
year = {2026},
note = {The code is available at
https://github.com/ZhaoWenzhao/WMCSFB.},
abstract = {Filter-decomposition-based group equivariant convolutional
neural networks (CNNs) have shown promising stability and
data efficiency for 3D image feature extraction. However,
these networks, which rely on parameter sharing and discrete
transformation groups, often underperform in modern deep
neural network architectures for processing volumetric
images with dense 3D textures, such as the common 3D medical
images. To address these limitations, this paper presents an
efficient non-parameter-sharing continuous 3D affine group
equivariant neural network for volumetric images. This
network uses an adaptive aggregation of Monte Carlo
augmented spherical Fourier–Bessel filter bases to improve
the efficiency and flexibility of 3D group equivariant CNNs
for volumetric data. Unlike existing methods that focus only
on angular orthogonality in filter bases, the introduced
spherical Bessel Fourier filter base incorporates both
angular and radial orthogonality to improve feature
extraction. Experiments on four medical image segmentation
datasets and two seismic datasets show that the proposed
methods achieve better affine group equivariance and
superior segmentation accuracy than existing 3D group
equivariant convolutional neural network layers,
significantly improving the training stability and data
efficiency of conventional CNN layers (at 0.05 significance
level).},
cin = {AG Radbruch},
ddc = {620},
cid = {I:(DE-2719)5000075},
pnm = {353 - Clinical and Health Care Research (POF4-353)},
pid = {G:(DE-HGF)POF4-353},
typ = {PUB:(DE-HGF)16},
doi = {10.1016/j.inffus.2025.103823},
url = {https://pub.dzne.de/record/283020},
}