DeepSphere: towards an equivariant graphbased spherical CNN
Abstract
Spherical data is found in many applications. By modeling the discretized sphere as a graph, we can accommodate nonuniformly distributed, partial, and changing samplings. Moreover, graph convolutions are computationally more efficient than spherical convolutions. As equivariance is desired to exploit rotational symmetries, we discuss how to approach rotation equivariance using the graph neural network introduced in Defferrard et al. (2016). Experiments show good performance on rotationinvariant learning problems. Code and examples are available at https://github.com/SwissDataScienceCenter/DeepSphere
 Publication:

arXiv eprints
 Pub Date:
 April 2019
 arXiv:
 arXiv:1904.05146
 Bibcode:
 2019arXiv190405146D
 Keywords:

 Computer Science  Machine Learning;
 Statistics  Machine Learning
 EPrint:
 published at the ICLR 2019 Workshop on Representation Learning on Graphs and Manifolds. arXiv admin note: text overlap with arXiv:1810.12186