Corpus ID: 202889315

B-Spline CNNs on Lie Groups

@article{Bekkers2020BSplineCO,
  title={B-Spline CNNs on Lie Groups},
  author={E. Bekkers},
  journal={ArXiv},
  year={2020},
  volume={abs/1909.12057}
}
  • E. Bekkers
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
Group convolutional neural networks (G-CNNs) can be used to improve classical CNNs by equipping them with the geometric structure of groups. Central in the success of G-CNNs is the lifting of feature maps to higher dimensional disentangled representations, in which data characteristics are effectively learned, geometric data-augmentations are made obsolete, and predictable behavior under geometric transformations (equivariance) is guaranteed via group theory. Currently, however, the practical… Expand

Figures and Tables from this paper

Spin-Weighted Spherical CNNs
Learning Equivariant Representations
A Dynamic Group Equivariant Convolutional Networks for Medical Image Analysis
Local Rotation Invariance in 3D CNNs
Roto-Translation Equivariant Convolutional Networks: Application to Histopathology Image Analysis
Group Equivariant Conditional Neural Processes
A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
...
1
2
3
4
...

References

SHOWING 1-10 OF 65 REFERENCES
SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels
Deformable Convolutional Networks
Gauge Equivariant Convolutional Networks and the Icosahedral CNN
Deep Symmetry Networks
Group Equivariant Convolutional Networks
Spherical CNNs
Learning Steerable Filters for Rotation Equivariant CNNs
Learning SO(3) Equivariant Representations with Spherical CNNs
3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data
...
1
2
3
4
5
...