Gauge Equivariant Convolutional Networks and the Icosahedral CNN

Abstract

The principle of equivariance to symmetry transformations enables a theoretically grounded approach to neural network architecture design. Equivariant networks have shown excellent performance and data efficiency on vision and medical imaging problems that exhibit symmetries. Here we show how this principle can be extended beyond global symmetries to local gauge transformations. This enables the development of a very general class of convolutional neural networks on manifolds that depend only on the intrinsic geometry, and which includes many popular methods from equivariant and geometric deep learning. We implement gauge equivariant CNNs for signals defined on the surface of the icosahedron, which provides a reasonable approximation of the sphere. By choosing to work with this very regular manifold, we are able to implement the gauge equivariant convolution using a single conv2d call, making it a highly scalable and practical alternative to Spherical CNNs. Using this method, we demonstrate substantial improvements over previous methods on the task of segmenting omnidirectional images and global climate patterns.

Proceedings of the International Conference on Machine Learning (ICML), 2019

References in corpus (1)

• Spherical CNNs on Unstructured Grids

Cited by in corpus (14)

• Stand-Alone Self-Attention in Vision Models
• CNNs on Surfaces using Rotation-Equivariant Features
• Scale-Equivariant Steerable Networks
• Co-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring In Data
• InMoDeGAN: Interpretable Motion Decomposition Generative Adversarial Network for Video Generation
• Rotation-Equivariant Deep Learning for Diffusion MRI
• Covariance in Physics and Convolutional Neural Networks
• Rotation-Invariant Autoencoders for Signals on Spheres
• ManifoldNorm: Extending normalizations on Riemannian Manifolds
• Affine Self Convolution
• RISA-Net: Rotation-Invariant Structure-Aware Network for Fine-Grained 3D Shape Retrieval
• Computational Analysis of Deformable Manifolds: from Geometric Modelling to Deep Learning
• Interpretable Image Clustering via Diffeomorphism-Aware K-Means
• Equivariant Point Network for 3D Point Cloud Analysis