Learning Robust and Discriminative Subspace With Low-Rank Constraints
Authors:
- 31 August 2015
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 27 (11) , 2160-2173
Abstract
In this paper, we aim at learning robust and discriminative subspaces from noisy data. Subspace learning is widely used in extracting discriminative features for classification. However, when data are contaminated with severe noise, the performance of most existing subspace learning methods would be limited. Recent advances in low-rank modeling provide effective solutions for removing noise or outliers contained in sample sets, which motivates us to take advantage of low-rank constraints in order to exploit robust and discriminative subspace for classification. In particular, we present a discriminative subspace learning method called the supervised regularization-based robust subspace (SRRS) approach, by incorporating the low-rank constraint. SRRS seeks low-rank representations from the noisy data, and learns a discriminative subspace from the recovered clean data jointly. A supervised regularization function is designed to make use of the class label information, and therefore to enhance the discriminability of subspace. Our approach is formulated as a constrained rank-minimization problem. We design an inexact augmented Lagrange multiplier optimization algorithm to solve it. Unlike the existing sparse representation and low-rank learning methods, our approach learns a low-dimensional subspace from recovered data, and explicitly incorporates the supervised information. Our approach and some baselines are evaluated on the COIL-100, ALOI, Extended YaleB, FERET, AR, and KinFace databases. The experimental results demonstrate the effectiveness of our approach, especially when the data contain considerable noise or variations.Keywords
Funding Information
- National Science Foundation Computer and Network Systems (1314484)
- Office of Naval Research (ONR) (N00014-12-1-1028)
- ONR Young Investigator (N00014-14-1-0484)
- Naval Post-Graduate School (N00244-15-1-0041)
- U.S. Army Research Office Young Investigator (W911NF-14-1-0218)
This publication has 42 references indexed in Scilit:
- Learning low-rank and discriminative dictionary for image classificationImage and Vision Computing, 2014
- Robust Subspace Discovery through Supervised Low-Rank Constraints2014
- Distributed Low-Rank Subspace Segmentation2013
- A Divide-and-Conquer Method for Scalable Low-Rank Latent Matrix Pursuit2013
- Low-Rank Structure Learning via Nonconvex Heuristic RecoveryIEEE Transactions on Neural Networks and Learning Systems, 2013
- Surveillance video coding via low-rank and sparse decomposition2012
- Moving Object Detection by Detecting Contiguous Outliers in the Low-Rank RepresentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- TILT: Transform Invariant Low-Rank TexturesInternational Journal of Computer Vision, 2012
- Subclass discriminant analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- Eigenfaces vs. Fisherfaces: recognition using class specific linear projectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997