Cobb, OJ; Wallis, CGR; Mavor-Parker, AN; Marignier, A; Price, MA; D'Avezac, M; McEwen, JD; (2021) Efficient Generalized Spherical CNNs. In: Proceedings of ICLR 2021 - 9th International Conference on Learning Representations. ICLR 2021 - 9th International Conference on Learning Representations: Vienna, Austria.

Preview

Text 3692_efficient_generalized_spherica.pdf - Published Version Download (445kB) | Preview

Abstract

Many problems across computer vision and the natural sciences require the analysis of spherical data, for which representations may be learned efficiently by encoding equivariance to rotational symmetries. We present a generalized spherical CNN framework that encompasses various existing approaches and allows them to be leveraged alongside each other. The only existing non-linear spherical CNN layer that is strictly equivariant has complexity OpC2L5q, where C is a measure of representational capacity and L the spherical harmonic bandlimit. Such a high computational cost often prohibits the use of strictly equivariant spherical CNNs. We develop two new strictly equivariant layers with reduced complexity OpCL4q and OpCL3 log Lq, making larger, more expressive models computationally feasible. Moreover, we adopt efficient sampling theory to achieve further computational savings. We show that these developments allow the construction of more expressive hybrid models that achieve state-of-the-art accuracy and parameter efficiency on spherical benchmark problems.

Download activity - last month

Export as JSONXMLCSV

Download activity - last 12 months

Export as JSONXMLCSV

Downloads by country - last 12 months

Export as JSONXMLCSV

Archive Staff Only

View Item