DeepAI AI Chat
Log In Sign Up

Geometry-aware Similarity Learning on SPD Manifolds for Visual Recognition

by   Zhiwu Huang, et al.
ETH Zurich

Symmetric Positive Definite (SPD) matrices have been widely used for data representation in many visual recognition tasks. The success mainly attributes to learning discriminative SPD matrices with encoding the Riemannian geometry of the underlying SPD manifold. In this paper, we propose a geometry-aware SPD similarity learning (SPDSL) framework to learn discriminative SPD features by directly pursuing manifold-manifold transformation matrix of column full-rank. Specifically, by exploiting the Riemannian geometry of the manifold of fixed-rank Positive Semidefinite (PSD) matrices, we present a new solution to reduce optimizing over the space of column full-rank transformation matrices to optimizing on the PSD manifold which has a well-established Riemannian structure. Under this solution, we exploit a new supervised SPD similarity learning technique to learn the transformation by regressing the similarities of selected SPD data pairs to their ground-truth similarities on the target SPD manifold. To optimize the proposed objective function, we further derive an algorithm on the PSD manifold. Evaluations on three visual classification tasks show the advantages of the proposed approach over the existing SPD-based discriminant learning methods.


From Manifold to Manifold: Geometry-Aware Dimensionality Reduction for SPD Matrices

Representing images and videos with Symmetric Positive Definite (SPD) ma...

Component SPD Matrices: A lower-dimensional discriminative data descriptor for image set classification

In the domain of pattern recognition, using the SPD (Symmetric Positive ...

Dimensionality Reduction on SPD Manifolds: The Emergence of Geometry-Aware Methods

Representing images and videos with Symmetric Positive Definite (SPD) ma...

A Unified Framework for Domain Adaptation using Metric Learning on Manifolds

We present a novel framework for domain adaptation, whereby both geometr...

Riemannian batch normalization for SPD neural networks

Covariance matrices have attracted attention for machine learning applic...

Geometry-aware Dynamic Movement Primitives

In many robot control problems, factors such as stiffness and damping ma...

Shape And Structure Preserving Differential Privacy

It is common for data structures such as images and shapes of 2D objects...