SOTAVerified

DeepSphere: a graph-based spherical CNN

2020-12-30ICLR 2020Code Available1· sign in to hype

Michaël Defferrard, Martino Milani, Frédérick Gusset, Nathanaël Perraudin

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

Designing a convolution for a spherical neural network requires a delicate tradeoff between efficiency and rotation equivariance. DeepSphere, a method based on a graph representation of the sampled sphere, strikes a controllable balance between these two desiderata. This contribution is twofold. First, we study both theoretically and empirically how equivariance is affected by the underlying graph with respect to the number of vertices and neighbors. Second, we evaluate DeepSphere on relevant problems. Experiments show state-of-the-art performance and demonstrates the efficiency and flexibility of this formulation. Perhaps surprisingly, comparison with previous work suggests that anisotropic filters might be an unnecessary price to pay. Our code is available at https://github.com/deepsphere

Reproductions