A General Theory of Equivariant CNNs on Homogeneous Spaces

Part of Advances in Neural Information Processing Systems 32 (NeurIPS 2019)

AuthorFeedback Bibtex MetaReview Metadata Paper Reviews Supplemental


Taco S. Cohen, Mario Geiger, Maurice Weiler


We present a general theory of Group equivariant Convolutional Neural Networks (G-CNNs) on homogeneous spaces such as Euclidean space and the sphere. Feature maps in these networks represent fields on a homogeneous base space, and layers are equivariant maps between spaces of fields. The theory enables a systematic classification of all existing G-CNNs in terms of their symmetry group, base space, and field type. We also answer a fundamental question: what is the most general kind of equivariant linear map between feature spaces (fields) of given types? We show that such maps correspond one-to-one with generalized convolutions with an equivariant kernel, and characterize the space of such kernels.