Skip navigation
Skip navigation

Efficient Learning to Label Images

Jia, Ke; Cheng, Li; Liu, Nianjun; Wang, Lei


Conditional random field methods (CRFs) have gained popularity for image labeling tasks in recent years. In this paper, we describe an alternative discriminative approach, by extending the large margin principle to incorporate spatial correlations among neighboring pixels. In particular, by explicitly enforcing the submodular condition, graph-cuts is conveniently integrated as the inference engine to attain the optimal label assignment efficiently. Our approach allows learning a model with...[Show more]

CollectionsANU Research Publications
Date published: 2010
Type: Conference paper
Source: Proceedings of The 23rd IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2010)
DOI: 10.1109/ICPR.2010.236


File Description SizeFormat Image
01_Jia_Efficient_Learning_to_Label_2010.pdf362.72 kBAdobe PDF    Request a copy

Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  20 July 2017/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator