Learning sparse conditional random fields to select features for land development classification
This article proposes a sparse conditional random field (SCRF) model to exploit contextual information for classification problems, and select relevant features to prevent overfitting derived from excessively large numbers of features. The sparsity arises from the use of Laplacian priors on the parameters of CRFs, which encourages the parameter estimates to be either significantly large or exactly zero. Since the Laplacian distribution is nondifferentiable at the origin, we developed a simple but efficient sub-gradient-based training algorithm to compute a maximum a posteriori (MAP) point estimate of the CRF parameters. We used SCRF for the classification between urban and non-urban areas in an optical remote sensing image database. The results attest to the accuracy, sparsity and effectiveness of the proposed model.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
Document Type: Research Article
Affiliations: ATR National Laboratory,School of Electronic Science and Engineering, National University of Defense Technology, Hunan, China
Publication date: August 10, 2011