Riemannian local mechanism for SPD neural networks

Chen, Ziheng, Xu, Tianyang, Wu, Xiao-Jun, Wang, Rui, Huang, Zhiwu and Kittler, Josef (2023) Riemannian local mechanism for SPD neural networks. In Association for the Advancement of Artificial Intelligence. 7104 - 7112 . (doi:10.1609/aaai.v37i6.25867).

Abstract

The Symmetric Positive Definite (SPD) matrices have received wide attention for data representation in many scientific areas. Although there are many different attempts to develop effective deep architectures for data processing on the Riemannian manifold of SPD matrices, very few solutions explicitly mine the local geometrical information in deep SPD feature representations. Given the great success of local mechanisms in Euclidean methods, we argue that it is of utmost importance to ensure the preservation of local geometric information in the SPD networks. We first analyse the convolution operator commonly used for capturing local information in Euclidean deep networks from the perspective of a higher level of abstraction afforded by category theory. Based on this analysis, we define the local information in the SPD manifold and design a multi-scale sub-manifold block for mining local geometry. Experiments involving multiple visual tasks validate the effectiveness of our approach.

This record has no associated files available for download.

Contributors

Author: Zhiwu Huang

Download statistics