Equivariant Networks for Pixelized Spheres

Abstract

Pixelizations of Platonic solids such as the cube and icosahedron have been widely used to represent spherical data, from climate records to Cosmic Microwave Background maps. Platonic solids have well-known global symmetries. Once we pixelize each face of the solid, each face also possesses its own local symmetries in the form of Euclidean isometries. One way to combine these symmetries is through a hierarchy. However, this approach does not adequately model the interplay between the two levels of symmetry transformations. We show how to model this interplay using ideas from group theory, identify the equivariant linear maps, and introduce equivariant padding that respects these symmetries. Deep networks that use these maps as their building blocks generalize gauge equivariant CNNs on pixelized spheres. These deep networks achieve state-of-the-art results on semantic segmentation for climate data and omnidirectional image processing. Code is available at https://git.io/JGiZA.

arXiv commentAccepted to ICML 2021

References in corpus (18)

• Joint 2D-3D-Semantic Data for Indoor Scene Understanding
• Group Equivariant Convolutional Networks
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• Rotation equivariant vector field networks
• DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
• Gauge Equivariant Convolutional Networks and the Icosahedral CNN
• An icosahedron-based method for pixelizing the celestial sphere
• Learning Spherical Convolution for Fast Features from 360° Imagery
• Equivariance Through Parameter-Sharing
• Invariant and Equivariant Graph Networks
• Covariant Compositional Networks For Learning Graphs
• Spherical CNNs on Unstructured Grids
• Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network
• LieTransformer: Equivariant self-attention for Lie Groups
• On the Universality of Rotation Equivariant Point Cloud Networks
• DeepSphere: a graph-based spherical CNN
• Spin-Weighted Spherical CNNs
• Equivariant Maps for Hierarchical Structures