Published March 17, 2024 | Version v1
Conference proceeding Open

A Lie Group Approach to Riemannian Batch Normalization

  • 1. ROR icon University of Trento
  • 2. ROR icon University of Louisville

Description

Manifold-valued measurements exist in numerous applications within computer vision and machine learning. Recent studies have extended Deep Neural Networks (DNNs) to manifolds, and concomitantly, normalization techniques have also been adapted to several manifolds, referred to as Riemannian normalization. Nonetheless, most of the existing Riemannian normalization methods have been derived in an ad hoc manner and only apply to specific manifolds. This paper establishes a unified framework for Riemannian Batch Normalization (RBN) techniques on Lie groups. Our framework offers the theoretical guarantee of controlling both the Riemannian mean and variance. Empirically, we focus on Symmetric Positive Definite (SPD) manifolds, which possess three distinct types of Lie group structures. Using the deformation concept, we generalize the existing Lie groups on SPD manifolds into three families of parameterized Lie groups. Specific normalization layers induced by these Lie groups are then proposed for SPD neural networks. We demonstrate the effectiveness of our approach through three sets of experiments: radar recognition, human action recognition, and electroencephalography (EEG) classification. The code is available at this https URL.

Files

2403.11261.pdf

Files (432.7 kB)

Name Size Download all
md5:878a6272e13b47bb2e86c4ec5bacc654
432.7 kB Preview Download

Additional details

Funding

ELIAS – European Lighthouse of AI for Sustainability 101120237
European Commission