Kernel Learning for Extrinsic Classification of Manifold Features
Authors:
- Raviteja VemulapalliRVRaviteja Vemulapalli
- Jaishanker K. PillaiJPJaishanker K. Pillai
- Rama ChellappaRCRama Chellappa
- 1 June 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1782-1789
Abstract
In computer vision applications, features often lie on Riemannian manifolds with known geometry. Popular learning algorithms such as discriminant analysis, partial least squares, support vector machines, etc., are not directly applicable to such features due to the non-Euclidean nature of the underlying spaces. Hence, classification is often performed in an extrinsic manner by mapping the manifolds to Euclidean spaces using kernels. However, for kernel based approaches, poor choice of kernel often results in reduced performance. In this paper, we address the issue of kernel selection for the classification of features that lie on Riemannian manifolds using the kernel learning approach. We propose two criteria for jointly learning the kernel and the classifier using a single optimization problem. Specifically, for the SVM classifier, we formulate the problem of learning a good kernel-classifier combination as a convex optimization problem and solve it efficiently following the multiple kernel learning approach. Experimental results on image set-based classification and activity recognition clearly demonstrate the superiority of the proposed approach over existing methods for classification of manifold features.Keywords
This publication has 22 references indexed in Scilit:
- Statistical Computations on Grassmann and Stiefel Manifolds for Image and Video-Based RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- Statistical analysis on Stiefel and Grassmann manifolds with applications in computer vision2008
- Pedestrian Detection via Classification on Riemannian ManifoldsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Boosted manifold principal angles for image set-based recognitionPattern Recognition, 2007
- Discriminative Learning and Recognition of Image Set Classes Using Canonical CorrelationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- A Riemannian Framework for Tensor ComputingInternational Journal of Computer Vision, 2006
- Matching shape sequences in video with applications in human movement analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- Beyond the point cloud2005
- Analyzing appearance and contour based methods for object categorization2003
- Using SeDuMi 1.02, A Matlab toolbox for optimization over symmetric conesOptimization Methods and Software, 1999