Sciweavers

Share
CVPR
2009
IEEE

Unsupervised Learning of Hierarchical Spatial Structures In Images

10 years 9 months ago
Unsupervised Learning of Hierarchical Spatial Structures In Images
The visual world demonstrates organized spatial patterns, among objects or regions in a scene, object-parts in an object, and low-level features in object-parts. These classes of spatial structures are inherently hierarchical in nature. Although seemingly quite different these spatial patterns are simply manifestations of different levels in a hierarchy. In this work, we present a unified approach to unsupervised learning of hierarchical spatial structures from a collection of images. Ours is a hierarchical rule-based model capturing spatial patterns, where each rule is represented by a star-graph. We propose an unsupervised EMstyle algorithm to learn our model from a collection of images. We show that the inference problem of determining the set of learnt rules instantiated in an image is equivalent to finding the minimum-cost Steiner tree in a directed acyclic graph. We evaluate our approach on a diverse set of data sets of object categories, natural outdoor scenes an...
Devi Parikh (Carnegie Mellon University), C. Lawre
Added 09 May 2009
Updated 02 Apr 2010
Type Conference
Year 2009
Where CVPR
Authors Devi Parikh (Carnegie Mellon University), C. Lawrence Zitnick (Microsoft Research), Tsuhan Chen (Carnegie Mellon University)
Comments (0)
books