UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Fully-connected CRFs with non-parametric pairwise potential

Campbell, NDF; Subr, K; Kautz, J; (2013) Fully-connected CRFs with non-parametric pairwise potential. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition. (pp. 1658 -1665). IEEE: USA. Green open access

[thumbnail of cvpr13_non_para_crf.pdf] PDF
Available under License : See the attached licence file.

Download (829kB)


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.

Type: Proceedings paper
Title: Fully-connected CRFs with non-parametric pairwise potential
Event: CVPR 2013
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/CVPR.2013.217
Publisher version: http://dx.doi.org/10.1109/CVPR.2013.217
Language: English
Additional information: © 2013 IEEE. Personal use of this material (accepted version) is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/1418254
Downloads since deposit
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item