Convolutional Networks for Spherical Signals
arXiv:1709.04893
Abstract
The success of convolutional networks in learning problems involving planar signals such as images is due to their ability to exploit the translation symmetry of the data distribution through weight sharing. Many areas of science and egineering deal with signals with other symmetries, such as rotation invariant data on the sphere. Examples include climate and weather science, astrophysics, and chemistry. In this paper we present spherical convolutional networks. These networks use convolutions on the sphere and rotation group, which results in rotational weight sharing and rotation equivariance. Using a synthetic spherical MNIST dataset, we show that spherical convolutional networks are very effective at dealing with rotationally invariant classification problems.
Cited by in corpus (18)
- Scale-Equivariant Steerable Networks
- A General Theory of Equivariant CNNs on Homogeneous Spaces
- Convolutions on Spherical Images
- Spherical Multi-Modal Place Recognition for Heterogeneous Sensor Systems
- Rotation-Equivariant Deep Learning for Diffusion MRI
- Convolutional Neural Networks on non-uniform geometrical signals using Euclidean spectral transformation
- A CNN for homogneous Riemannian manifolds with applications to Neuroimaging
- ChaRRNets: Channel Robust Representation Networks for RF Fingerprinting
- Scattering Networks on the Sphere for Scalable and Rotationally Equivariant Spherical CNNs
- SurReal: Complex-Valued Learning as Principled Transformations on a Scaling and Rotation Manifold
- Pano Popups: Indoor 3D Reconstruction with a Plane-Aware Network
- ODE-CNN: Omnidirectional Depth Extension Networks
- VolterraNet: A higher order convolutional network with group equivariance for homogeneous manifolds
- POIRot: A rotation invariant omni-directional pointnet
- PCLs: Geometry-aware Neural Reconstruction of 3D Pose with Perspective Crop Layers
- Applying VertexShuffle Toward 360-Degree Video Super-Resolution on Focused-Icosahedral-Mesh
- Learning Compressible 360° Video Isomers
- An "augmentation-free" rotation invariant classification scheme on point-cloud and its application to neuroimaging