Efficient discriminative learning of parts-based models
Authors:
- 1 September 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 552-559
Abstract
Supervised learning of a parts-based model can be formulated as an optimization problem with a large (exponential in the number of parts) set of constraints. We show how this seemingly difficult problem can be solved by (i) reducing it to an equivalent convex problem with a small, polynomial number of constraints (taking advantage of the fact that the model is tree-structured and the potentials have a special form); and (ii) obtaining the globally optimal model using an efficient dual decomposition strategy. Each component of the dual decomposition is solved by a modified version of the highly optimized SVM-Light algorithm. To demonstrate the effectiveness of our approach, we learn human upper body models using two challenging, publicly available datasets. Our model accounts for the articulation of humans as well as the occlusion of parts. We compare our method with a baseline iterative strategy as well as a state of the art algorithm and show significant efficiency improvements.Keywords
This publication has 14 references indexed in Scilit:
- Progressive search space reduction for human pose estimation2008
- Learning for stereo vision using the structured support vector machine2008
- Multiple Instance Classification via Successive Linear ProgrammingJournal of Optimization Theory and Applications, 2007
- MRF Optimization via Dual Decomposition: Message-Passing Revisited2007
- OBJ CUT2005
- Histograms of Oriented Gradients for Human Detection2005
- Efficient belief propagation for early vision2004
- Support vector machine learning for interdependent and structured output spaces2004
- Efficient matching of pictorial structures2002
- The Nature of Statistical Learning Theory1995