- TL;DR: This paper proposes a scalable equivariant spherical convolution.
- Abstract: Spherical CNNs are convolutional neural networks that can process signals on the sphere, such as global climate and weather patterns or omnidirectional images. Over the last few years, a number of spherical convolution methods have been proposed, based on generalized spherical FFTs, graph convolutions, and other ideas. However, none of these methods is simultaneously equivariant to 3D rotations, able to detect anisotropic patterns, computationally efficient, agnostic to the type of sample grid used, and able to deal with signals defined on only a part of the sphere. To address these limitations, we introduce the Gauge Equivariant Spherical CNN. Our method is based on the recently proposed theory of Gauge Equivariant CNNs, which is in principle applicable to signals on any manifold, and which can be computed on any set of local charts covering all of the manifold or only part of it. In this paper we show how this method can be implemented efficiently for the sphere, and show that the resulting method is fast, numerically accurate, and achieves good results on the widely used benchmark problems of climate pattern segmentation and omnidirectional semantic segmentation.
- Keywords: deep learning, convolutional networks, equivariance, gauge equivariance, symmetry, geometric deep learning, manifold convolution