Efficient piecewise learning for conditional random fields

• Published in: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition pp. 895 - 901
• Main Authors: Alahari, Karteek, Russell, Chris, Torr, Philip H S
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2010
• Subjects: Belief propagation; Computer vision; Costs; Inference algorithms; Labeling; Learning systems; Optimization methods; Parameter estimation; Random variables; Training data

Conditional Random Field models have proved effective for several low-level computer vision problems. Inference in these models involves solving a combinatorial optimization problem, with methods such as graph cuts, belief propagation. Although several methods have been proposed to learn the model p...