Efficient learning of relational object class models

Aharon Bar-Hillel*, Daphna Weinshall

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

23 Scopus citations


We present an efficient method for learning part-based object class models from unsegmented images represented as sets of salient features. A model includes parts' appearance, as well as location and scale relations between parts. The object class is generatively modeled using a simple Bayesian network with a central hidden node containing location and scale information, and nodes describing object parts. The model's parameters, however, are optimized to reduce a loss function of the training error, as in discriminative methods. We show how boosting techniques can be extended to optimize the relational model proposed, with complexity linear in the number of parts and the number of features per image. This efficiency allows our method to learn relational models with many parts and features. The method has an advantage over purely generative and purely discriminative approaches for learning from sets of salient features, since generative method often use a small number of parts and features, while discriminative methods tend to ignore geometrical relations between parts. Experimental results are described, using some bench-mark data sets and three sets of newly collected data, showing the relative merits of our method in recognition and localization tasks.

Original languageAmerican English
Pages (from-to)175-198
Number of pages24
JournalInternational Journal of Computer Vision
Issue number1-3
StatePublished - May 2008


  • Boosting
  • Generative models
  • Object class recognition
  • Object localization
  • Weakly supervised learning


Dive into the research topics of 'Efficient learning of relational object class models'. Together they form a unique fingerprint.

Cite this