Fully-Connected CRFs with Non-Parametric Pairwise Potentials

Neill D. F. Campbell, Jan Kautz, Katric Subr

Research output: Chapter in Book/Report/Conference proceedingConference contribution

19 Citations (Scopus)

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.

Original languageEnglish
Title of host publication2013 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
Place of PublicationNEW YORK
PublisherIEEE
Pages1658-1665
Number of pages8
DOIs
Publication statusPublished - 2013
EventIEEE Conference on Computer Vision and Pattern Recognition 2013 - Portland, Portland, OR, United States
Duration: 23 Jun 201328 Jun 2013

Publication series

NameIEEE Conference on Computer Vision and Pattern Recognition
PublisherIEEE
ISSN (Print)1063-6919

Conference

ConferenceIEEE Conference on Computer Vision and Pattern Recognition 2013
Abbreviated titleCVPR 2013
Country/TerritoryUnited States
CityPortland, OR
Period23/06/1328/06/13

Keywords

  • ENERGY MINIMIZATION

Fingerprint

Dive into the research topics of 'Fully-Connected CRFs with Non-Parametric Pairwise Potentials'. Together they form a unique fingerprint.

Cite this