2006 DiscriminativeRandomFields

(Kumar & Hebert, 2006) ⇒ Sanjiv Kumar, and Martial Hebert. (2006). “Discriminative Random Fields.” In: International Journal of Computer Vision, 68(2). doi:10.1007/s11263-006-7007-9

Subject Headings: Supervised Discriminative Classifiers.

Notes

Cited By

Quotes

Author Keywords

Discriminative Classifiers; Discriminative Random Fields; Graphical Models; Image Classification; Markov Random Field; Spatial Interactions

Abstract

In this research we address the problem of classification and labeling of regions given a single static natural image. Natural images exhibit strong spatial dependencies, and modeling these dependencies in a principled manner is crucial to achieve good classification accuracy. In this work, we present Discriminative Random Fields (DRFs) to model spatial interactions in images in a discriminative framework based on the concept of Conditional Random Fields proposed by lafferty et al.(2001). The DRFs classify image regions by incorporating neighborhood spatial interactions in the labels as well as the observed data. The DRF framework offers several advantages over the conventional Markov Random Field (MRF) framework. First, the DRFs allow to relax the strong assumption of conditional independence of the observed data generally used in the MRF framework for tractability. This assumption is too restrictive for a large number of applications in computer vision. Second, the DRFs derive their classification power by exploiting the probabilistic discriminative models instead of the generative models used for modeling observations in the MRF framework. Third, the interaction in labels in DRFs is based on the idea of pairwise discrimination of the observed data making it data-adaptive instead of being fixed a priori as in MRFs. Finally, all the parameters in the DRF model are estimated simultaneously from the training data unlike the MRF framework where the likelihood parameters are usually learned separately from the field parameters. We present preliminary experiments with man-made structure detection and binary image restoration tasks, and compare the DRF results with the MRF results.

References

,

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2006 DiscriminativeRandomFields	Sanjiv Kumar Martial Hebert			Discriminative Random Fields				10.1007/s11263-006-7007-9		2006