Active boundary annotation using random MAP perturbations
Author(s)Maji, Subhransu; Hazan, Tamir; Jaakkola, Tommi S
MetadataShow full item record
We address the problem of efficiently annotating labels of objects when they are structured. Often the distribution over labels can be described using a joint potential function over the labels for which sampling is provably hard but efficient maximum a-posteriori (MAP) solvers exist. In this setting we develop novel entropy bounds that are based on the expected amount of perturbation to the potential function that is needed to change MAP decisions. By reasoning about the entropy reduction and cost tradeoff, our algorithm actively selects the next annotation task. As an example of our framework we propose a boundary refinement task which can used to obtain pixelaccurate image boundaries much faster than traditional tools by focussing on parts of the image for refinement in a multi-scale manner.
DepartmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Proceedings of the 17th International Conference on Artificial Intelligence and Statistics (AISTATS)
Maji, Subhransu, Tamir Hazan, and Tommi Jaakkola. "Active Boundary Annotation using Random MAP Perturbations." Proceedings of the 17th International Conference on Artificial Intelligence and Statistics (AISTATS), 22-25 April, 2014, Reykjavik, Iceland, PMLR, 2014. © The Authors
Author's final manuscript