Sciweavers

Share
ECCV
2008
Springer

Unsupervised Structure Learning: Hierarchical Recursive Composition, Suspicious Coincidence and Competitive Exclusion

11 years 3 months ago
Unsupervised Structure Learning: Hierarchical Recursive Composition, Suspicious Coincidence and Competitive Exclusion
Abstract. We describe a new method for unsupervised structure learning of a hierarchical compositional model (HCM) for deformable objects. The learning is unsupervised in the sense that we are given a training dataset of images containing the object in cluttered backgrounds but we do not know the position or boundary of the object. The structure learning is performed by a bottom-up and top-down process. The bottom-up process is a novel form of hierarchical clustering which recursively composes proposals for simple structures to generate proposals for more complex structures. We combine standard clustering with the suspicious coincidence principle and the competitive exclusion principle to prune the number of proposals to a practical number and avoid an exponential explosion of possible structures. The hierarchical clustering stops automatically, when it fails to generate new proposals, and outputs a proposal for the object model. The top-down process validates the proposals and fills i...
Long Zhu, Chenxi Lin, Haoda Huang, Yuanhao Chen, A
Added 15 Oct 2009
Updated 15 Oct 2009
Type Conference
Year 2008
Where ECCV
Authors Long Zhu, Chenxi Lin, Haoda Huang, Yuanhao Chen, Alan L. Yuille
Comments (0)
books