Riemannian batch normalization for SPD neural networks

Abstract

Covariance matrices have attracted attention for machine learning applications due to their capacity to capture interesting structure in the data. The main challenge is that one needs to take into account the particular geometry of the Riemannian manifold of symmetric positive definite (SPD) matrices they belong to. In the context of deep networks, several architectures for these matrices have recently been proposed. In our article, we introduce a Riemannian batch normalization (batchnorm) algorithm, which generalizes the one used in Euclidean nets. This novel layer makes use of geometric operations on the manifold, notably the Riemannian barycenter, parallel transport and non-linear structured matrix transformations. We derive a new manifold-constrained gradient descent algorithm working in the space of SPD matrices, allowing to learn the batchnorm layer. We validate our proposed approach with experiments in three different contexts on diverse data types: a drone recognition dataset from radar observations, and on emotion and action recognition datasets from video and motion capture data. Experiments show that the Riemannian batchnorm systematically gives better classification performance compared with leading methods and a remarkable robustness to lack of data.

arXiv commentAccepted to NeurIPS 2019

Cited by in corpus (11)

• Tensor-CSPNet: A Novel Geometric Deep Learning Framework for Motor Imagery Classification
• Normalization Techniques in Training DNNs: Methodology, Analysis and Application
• Graph Neural Networks on SPD Manifolds for Motor Imagery Classification: A Perspective from the Time-Frequency Analysis
• Geoopt: Riemannian Optimization in PyTorch
• MVC-Net: A Convolutional Neural Network Architecture for Manifold-Valued Images With Applications
• R-Mixup: Riemannian Mixup for Biological Networks
• A reduced parallel transport equation on Lie Groups with a left-invariant metric
• ManifoldNorm: Extending normalizations on Riemannian Manifolds
• 2021 BEETL Competition: Advancing Transfer Learning for Subject Independence & Heterogenous EEG Data Sets
• Differentiating through the Fréchet Mean
• GeomNet: A Neural Network Based on Riemannian Geometries of SPD Matrix Space and Cholesky Space for 3D Skeleton-Based Interaction Recognition