Research

Fully-connected CRFs with non-parametric pairwise potential


Reference:

Campbell, N.D.F., Subr, K. and Kautz, J., 2013. Fully-connected CRFs with non-parametric pairwise potential. IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Related documents:

This repository does not currently have the full-text of this item.
You may be able to access a copy if URLs are provided below. (Contact Author)

Official URL:

http://dx.doi.org/10.1109/CVPR.2013.217

Related URLs:

Abstract

Conditional Random Fields (CRFs) are used for diverse tasks, ranging from image denoising to object recognition. For images, they are commonly defined as a graph with nodes corresponding to individual pixels and pairwise links that connect nodes to their immediate neighbors. Recent work has shown that fully-connected CRFs, where each node is connected to every other node, can be solved efficiently under the restriction that the pairwise term is a Gaussian kernel over a Euclidean feature space. In this paper, we generalize the pairwise terms to a non-linear dissimilarity measure that is not required to be a distance metric. To this end, we propose a density estimation technique to derive conditional pairwise potentials in a non-parametric manner. We then use an efficient embedding technique to estimate an approximate Euclidean feature space for these potentials, in which the pairwise term can still be expressed as a Gaussian kernel. We demonstrate that the use of non-parametric models for the pairwise interactions, conditioned on the input data, greatly increases expressive power whilst maintaining efficient inference.

Details

Item Type Articles
CreatorsCampbell, N.D.F., Subr, K. and Kautz, J.
DOI10.1109/CVPR.2013.217
Related URLs
URLURL Type
http://www.scopus.com/inward/record.url?scp=84887355384&partnerID=8YFLogxKUNSPECIFIED
DepartmentsFaculty of Science > Computer Science
RefereedYes
StatusPublished
ID Code41566

Export

Actions (login required)

View Item