Similarity-based cross-layered hierarchical representation for object categorization

S. Fidler, M. Boben, A. Leonardis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

45 Citations (Scopus)


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. ©2008 IEEE.
Original languageEnglish
Title of host publicationComputer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference
PublisherIEEE Computer Society Press
Number of pages8
ISBN (Electronic)978-1424422432
ISBN (Print)978-1424422425
Publication statusPublished - Jun 2008
EventCVPR 2008 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Alaska, Anchorage, United States
Duration: 23 Jun 200828 Jun 2008


ConferenceCVPR 2008 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Country/TerritoryUnited States


Dive into the research topics of 'Similarity-based cross-layered hierarchical representation for object categorization'. Together they form a unique fingerprint.

Cite this