Subordinate class recognition using relational object models

Aharon Bar Hillel, Daphna Weinshall

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

12 Scopus citations

Abstract

We address the problem of sub-ordinate class recognition, like the distinction between different types of motorcycles. Our approach is motivated by observations from cognitive psychology, which identify parts as the defining component of basic level categories (like motorcycles), while sub-ordinate categories are more often defined by part properties (like'jagged wheels'). Accordingly, we suggest a two-stage algorithm: First, a relational part based object model is learnt using unsegmented object images from the inclusive class (e.g., motorcycles in general). The model is then used to build a class-specific vector representation for images, where each entry corresponds to a model's part. In the second stage we train a standard discriminative classifier to classify subclass instances (e.g., cross motorcycles) based on the class-specific vector representation. We describe extensive experimental results with several subclasses. The proposed algorithm typically gives better results than a competing one-step algorithm, or a two stage algorithm where classification is based on a model of the sub-ordinate class.

Original languageAmerican English
Title of host publicationNIPS 2006
Subtitle of host publicationProceedings of the 19th International Conference on Neural Information Processing Systems
EditorsBernhard Scholkopf, John C. Platt, Thomas Hofmann
PublisherMIT Press Journals
Pages73-80
Number of pages8
ISBN (Electronic)0262195682, 9780262195683
StatePublished - 2006
Event19th International Conference on Neural Information Processing Systems, NIPS 2006 - Vancouver, Canada
Duration: 4 Dec 20067 Dec 2006

Publication series

NameNIPS 2006: Proceedings of the 19th International Conference on Neural Information Processing Systems

Conference

Conference19th International Conference on Neural Information Processing Systems, NIPS 2006
Country/TerritoryCanada
CityVancouver
Period4/12/067/12/06

Bibliographical note

Publisher Copyright:
© NIPS 2006.All rights reserved

Fingerprint

Dive into the research topics of 'Subordinate class recognition using relational object models'. Together they form a unique fingerprint.

Cite this