A General Theory of Equivariant CNNs on Homogeneous Spaces

Abstract

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 consider a fundamental question: what is the most general kind of equivariant linear map between feature spaces (fields) of given types? Following Mackey, we show that such maps correspond one-to-one with convolutions using equivariant kernels, and characterize the space of such kernels.

References in corpus (21)

• Geometric deep learning: going beyond Euclidean data
• Understanding Deep Convolutional Networks
• Group Equivariant Convolutional Networks
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups
• 3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data
• Rotation equivariant vector field networks
• DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
• Exploiting Cyclic Symmetry in Convolutional Neural Networks
• Universal Invariant and Equivariant Graph Neural Networks
• Equivariance Through Parameter-Sharing
• General $E(2)$-Equivariant Steerable CNNs
• Invariant and Equivariant Graph Networks
• Covariant Compositional Networks For Learning Graphs
• 3D G-CNNs for Pulmonary Nodule Detection
• N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentials
• Convolutional Networks for Spherical Signals
• Deep Scale-spaces: Equivariance Over Scale
• Scale Steerable Filters for Locally Scale-Invariant Convolutional Neural Networks
• Intertwiners between Induced Representations (with Applications to the Theory of Equivariant Neural Networks)
• Gauge Theories and Fiber Bundles: Definitions, Pictures, and Results

Cited by in corpus (10)

• Gauge Equivariant Convolutional Networks and the Icosahedral CNN
• Deep Scale-spaces: Equivariance Over Scale
• A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
• Gauge $\times$ Gauge $=$ Gravity on Homogeneous Spaces using Tensor Convolutions
• B-Spline CNNs on Lie Groups
• Category Theory in Machine Learning
• ChaRRNets: Channel Robust Representation Networks for RF Fingerprinting
• Grounding inductive biases in natural images:invariance stems from variations in data
• Affine Self Convolution
• VolterraNet: A higher order convolutional network with group equivariance for homogeneous manifolds