Contextual Classification with Functional Max-Margin Markov Networks - Robotics Institute Carnegie Mellon University

Contextual Classification with Functional Max-Margin Markov Networks

Conference Paper, Proceedings of (CVPR) Computer Vision and Pattern Recognition, pp. 975 - 982, June, 2009

Abstract

We address the problem of label assignment in computer vision: given a novel 3-D or 2-D scene, we wish to assign a unique label to every site (voxel, pixel, superpixel, etc.). To this end, the Markov Random Field framework has proven to be a model of choice as it uses contextual information to yield improved classification results over locally independent classifiers. In this work we adapt a functional gradient approach for learning high-dimensional parameters of random fields in order to perform discrete, multi-label classification. With this approach we can learn robust models involving high-order interactions better than the previously used learning method. We validate the approach in the context of point cloud classification and improve the state of the art. In addition, we successfully demonstrate the generality of the approach on the challenging vision problem of recovering 3-D geometric surfaces from images. The data set is available at: http://www.cs.cmu.edu/~vmr/datasets/oakland_3d/cvpr09/doc/

Notes
Erratum: the last line in Algorithm 2 should be: return max(0, 1+(p-|c|)/Q)

BibTeX

@conference{Munoz-2009-10227,
author = {Daniel Munoz and J. Andrew (Drew) Bagnell and Nicolas Vandapel and Martial Hebert},
title = {Contextual Classification with Functional Max-Margin Markov Networks},
booktitle = {Proceedings of (CVPR) Computer Vision and Pattern Recognition},
year = {2009},
month = {June},
pages = {975 - 982},
}