An important problem in image labeling concerns learning with images labeled at varying levels of specificity. We propose an approach that can incorporate images with labels drawn...
This paper introduces an approach for handling complex labelling problems driven by local constraints. The purpose is illustrated by two applications: detection of the road networ...
This paper introduces a novel solver, namely cross entropy (CE), into the MRF theory for medical image segmentation. The solver, which is based on the theory of rare event simulati...
Discriminative training of graphical models can be expensive if the variables have large cardinality, even if the graphical structure is tractable. In such cases, pseudolikelihood...