PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Similarity-based cross-layered hierarchical representation for object categorization.
Marko Boben, Sanja Fidler and Aleš Leonardis
In: IEEE Computer Society Conference on Computer Vision and Pattern R 2008, 24-26 June 2008, Anchorage, Alaska.


This paper proposes a new concept in hierarchical representations that exploits features of different granularity and specificity coming from all layers of the hierarchy. The concept is realized within a cross-layered compositional representation learned from the visual data. We show how similarity connections among discrete labels within and across hierarchical layers can be established in order to produce a set of layer-independent shape-terminals, i.e. shapinals. We thus break the traditional notion of hierarchies and show how the category-specific layers can make use of all the necessary features stemming from all hierarchical layers. This, on the one hand, brings higher generalization into the representation, yet on the other hand, it also encodes the notion of scales directly into the hierarchy, thus enabling a multi-scale representation of object categories. By focusing on shape information only, the approach is tested on the Caltech 101 dataset demonstrating good performance in comparison with other state-of-the-art methods.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Talk)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Theory & Algorithms
ID Code:8197
Deposited By:Boris Horvat
Deposited On:21 February 2012