DeepSphere: towards an equivariant graph-based spherical CNN
This work addresses spherical data processing for applications like geospatial or medical imaging, but it is incremental as it builds on existing graph neural network methods.
The authors tackled the problem of processing spherical data with non-uniform or partial samplings by modeling the discretized sphere as a graph, achieving good performance on rotation-invariant learning problems.
Spherical data is found in many applications. By modeling the discretized sphere as a graph, we can accommodate non-uniformly 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 rotation-invariant learning problems. Code and examples are available at https://github.com/SwissDataScienceCenter/DeepSphere