DeepSphere: a graph-based spherical CNN

Michaël Defferrard, Martino Milani, Frédérick Gusset, Nathanaël Perraudin

Keywords: equivariance, graph networks

Thurs Session 2 (08:00-10:00 GMT) [Live QA] [Cal]
Thurs Session 3 (12:00-14:00 GMT) [Live QA] [Cal]
Thursday: Graphs and Representations

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 discretized 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 pixels 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.

Similar Papers

PairNorm: Tackling Oversmoothing in GNNs
Lingxiao Zhao, Leman Akoglu,
Masked Based Unsupervised Content Transfer
Ron Mokady, Sagie Benaim, Lior Wolf, Amit Bermano,
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut,
AtomNAS: Fine-Grained End-to-End Neural Architecture Search
Jieru Mei, Yingwei Li, Xiaochen Lian, Xiaojie Jin, Linjie Yang, Alan Yuille, Jianchao Yang,