K-Tangent Spaces on Riemannian Manifolds for Improved Pedestrian Detection
For covariance-based image descriptors, taking into account the curvature of the corresponding feature space has been shown to improve discrimination performance. This is often done through representing the descriptors as points on Riemannian manifolds, with the discrimination accomplished on a tangent space. However, such treatment is restrictive as distances between arbitrary points on the tangent space do not represent true geodesic distances, and hence do not represent the manifold structure accurately. In this paper we propose a general discriminative model based on the combination of several tangent spaces, in order to preserve more details of the structure. The model can be used as a weak learner in a boosting-based pedestrian detection framework. Experiments on the challenging INRIA and DaimlerChrysler datasets show that the proposed model leads to considerably higher performance than methods based on histograms of oriented gradients as well as previous Riemannian-based techniques.
Code (0)
등록된 구현이 없습니다.
Tasks
Pedestrian DetectionSimilar Papers 제목 키워드 기반
Riemannian MeanFlow for One-Step Generation on Manifolds
Flow Matching enables simulation-free training of generative models on Riemannian manifolds, yet sampling typically still relies on numerically integrating a probability-flow ODE. We propose Riemannian MeanFlow (RMF), ex…
Multi-Task LearningPR-CapsNet: Pseudo-Riemannian Capsule Network with Adaptive Curvature Routing for Graph Learning
Capsule Networks (CapsNets) show exceptional graph representation capacity via dynamic routing and vectorized hierarchical representations, but they model the complex geometries of real\-world graphs poorly by fixed\-cur…
Graph Representation LearningGraph ClassificationGraph LearningFoundations of Riemannian Geometry for Riemannian Optimization: A Monograph with Detailed Derivations
Riemannian geometry provides the fundamental framework for optimization on nonlinear spaces such as matrix manifolds, which arise in machine learning, signal processing, and robotics. While the underlying theory is class…
Gaussian Differential Privacy on Riemannian Manifolds
We develop an advanced approach for extending Gaussian Differential Privacy (GDP) to general Riemannian manifolds. The concept of GDP stands out as a prominent privacy definition that strongly warrants extension to manif…
Dimensionality Reduction on Riemannian Manifolds in Data Analysis
In this work, we investigate Riemannian geometry based dimensionality reduction methods that respect the underlying manifold structure of the data. In particular, we focus on Principal Geodesic Analysis (PGA) as a nonlin…
Dimensionality Reduction