2 papers
cs.CV2026
Adaptive aggregation of Monte Carlo augmented decomposed filters for efficient group-equivariant convolutional neural network
Wenzhao Zhao, Barbara D. Wichtmann, Steffen Albert +3
Group-equivariant convolutional neural networks (G-CNN) heavily rely on parameter sharing to increase CNN's data efficiency and performance. However, the parameter-sharing strategy…
cs.CV2026
Efficient 3D affinely equivariant CNNs with adaptive fusion of augmented spherical Fourier-Bessel bases
Wenzhao Zhao, Steffen Albert, Barbara D. Wichtmann +4
Filter-decomposition-based group equivariant convolutional neural networks (CNNs) have shown promising stability and data efficiency for 3D image feature extraction. However, these…