Exploiting object hierarchy: Combining models from different category levels

Alon Zweig*, Daphna Weinshall

*Corresponding author for this work

Research output: Contribution to conferencePaperpeer-review

89 Scopus citations


We investigated the computational properties of natural object hierarchy in the context of constellation object class models, and its utility for object class recognition. We first observed an interesting computational property of the object hierarchy: comparing the recognition rate when using models of objects at different levels, the higher more inclusive levels (e.g., Closed-Frame Vehicles or Vehicles) exhibit higher recall but lower precision when compared with the class specific level (e.g., bus). These inherent differences suggest that combining object classifiers from different hierarchical levels into a single classifier may improve classification, as it appears like these models capture different aspects of the object. We describe a method to combine these classifiers, and analyze the conditions under which improvement can be guaranteed. When given a small sample of a new object class, we describe a method to transfer knowledge across the tree hierarchy, between related objects. Finally, we describe extensive experiments using object hierarchies obtained from publicly available datasets, and show that the combined classifiers significantly improve recognition results.

Original languageAmerican English
StatePublished - 2007
Event2007 IEEE 11th International Conference on Computer Vision, ICCV - Rio de Janeiro, Brazil
Duration: 14 Oct 200721 Oct 2007


Conference2007 IEEE 11th International Conference on Computer Vision, ICCV
CityRio de Janeiro


Dive into the research topics of 'Exploiting object hierarchy: Combining models from different category levels'. Together they form a unique fingerprint.

Cite this