A Riemannian Network for SPD Matrix Learning
arXiv:1608.04233
Abstract
Symmetric Positive Definite (SPD) matrix learning methods have become popular in many image and video processing tasks, thanks to their ability to learn appropriate statistical representations while respecting Riemannian geometry of underlying SPD manifolds. In this paper we build a Riemannian network architecture to open up a new direction of SPD matrix non-linear learning in a deep model. In particular, we devise bilinear mapping layers to transform input SPD matrices to more desirable SPD matrices, exploit eigenvalue rectification layers to apply a non-linear activation function to the new SPD matrices, and design an eigenvalue logarithm layer to perform Riemannian computing on the resulting SPD matrices for regular output layers. For training the proposed deep network, we exploit a new backpropagation with a variant of stochastic gradient descent on Stiefel manifolds to update the structured connection weights and the involved SPD matrix data. We show through experiments that the proposed SPD matrix network can be simply trained and outperform existing SPD matrix learning and state-of-the-art methods in three typical visual classification tasks.
Revised arXiv version, AAAI-17 camera-ready
Cited by in corpus (5)
- Recurrent Embedding Aggregation Network for Video Face Recognition
- When Kernel Methods meet Feature Learning: Log-Covariance Network for Action Recognition from Skeletal Data
- Constructing the Matrix Multilayer Perceptron and its Application to the VAE
- Skeleton-Based Hand Gesture Recognition by Learning SPD Matrices with Neural Networks
- Riemannian joint dimensionality reduction and dictionary learning on symmetric positive definite manifold