Sciweavers

Share
NIPS
2003

Discriminative Fields for Modeling Spatial Dependencies in Natural Images

9 years 15 days ago
Discriminative Fields for Modeling Spatial Dependencies in Natural Images
In this paper we present Discriminative Random Fields (DRF), a discriminative framework for the classification of natural image regions by incorporating neighborhood spatial dependencies in the labels as well as the observed data. The proposed model exploits local discriminative models and allows to relax the assumption of conditional independence of the observed data given the labels, commonly used in the Markov Random Field (MRF) framework. The parameters of the DRF model are learned using penalized maximum pseudo-likelihood method. Furthermore, the form of the DRF model allows the MAP inference for binary classification problems using the graph min-cut algorithms. The performance of the model was verified on the synthetic as well as the real-world images. The DRF model outperforms the MRF model in the experiments.
Sanjiv Kumar, Martial Hebert
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2003
Where NIPS
Authors Sanjiv Kumar, Martial Hebert
Comments (0)
books