Learning Structured Outputs from Partial Labels using Forest Ensemble
This addresses the problem of learning structured outputs with partial labels, which is incremental as it builds on existing tree-structured models for practical scenarios like surveillance.
The paper tackles the challenge of learning structured outputs with general structures by proposing AdaBoost.MRF, an efficient boosting-based algorithm that handles partial labeling and is guaranteed to converge. It applies the method to an indoor video surveillance scenario, modeling activities at multiple levels.
Learning structured outputs with general structures is computationally challenging, except for tree-structured models. Thus we propose an efficient boosting-based algorithm AdaBoost.MRF for this task. The idea is based on the realization that a graph is a superimposition of trees. Different from most existing work, our algorithm can handle partial labelling, and thus is particularly attractive in practice where reliable labels are often sparsely observed. In addition, our method works exclusively on trees and thus is guaranteed to converge. We apply the AdaBoost.MRF algorithm to an indoor video surveillance scenario, where activities are modelled at multiple levels.