A Caltech Library Service

Towards Automatic Discovery of Object Categories

Weber, M. and Welling, M. and Perona, P. (2000) Towards Automatic Discovery of Object Categories. In: IEEE Conference on Computer Vision and Pattern Recognition. IEEE Conference on Computer Vision and Pattern Recognition, Proceedings. IEEE Computer Society , Los Alamitos, CA, pp. 101-108. ISBN 0-7695-0662-3.

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


We propose a method to learn heterogeneous models of object classes for visual recognition. The training images contain a preponderance of clutter and learning is unsupervised. Our models represent objects as probabilistic constellations of rigid parts (features). The variability within a class is represented by a joint probability density function on the shape of the constellation and the appearance of the parts. Our method automatically identifies distinctive features in the training set. The set of model parameters is then learned using expectation maximization (see the companion paper [11] for details). When trained on different, unlabeled and unsegmented views of a class of objects, each component of the mixture model can adapt to represent a subset of the views. Similarly, different component models can also “specialize” on sub-classes of an object class. Experiments on images of human heads, leaves from different species of trees, and motor-cars demonstrate that the method works well over a wide variety of objects.

Item Type:Book Section
Related URLs:
Perona, P.0000-0002-7583-5809
Additional Information:© 2000 IEEE. Date of Current Version: 06 August 2002. Funded by the NSF Engineering Research Center for Neuromorphic Systems Engineering (CNSE) at Caltech (NSF9402726), and an NSF National Young Investigator Award to P.P. (NSF9457618). M. Welling was supported by the Sloan Foundation. We are also very grateful to Rob Fergus, Catharine Stebbins and Justin Smith for helping with collecting the databases. We are grateful to Thomas Leung, Mike Burl, Jitendra Malik and David Forsyth for many helpful comments.
Funding AgencyGrant Number
Caltech NSF Engineering Research Center for Neuromorphic Systems Engineering (CNSE)NSF9402726
NSF National Young Investigator AwardNSF9457618
Sloan FoundationUNSPECIFIED
Other Numbering System:
Other Numbering System NameOther Numbering System ID
INSPEC Accession Number6651766
Series Name:IEEE Conference on Computer Vision and Pattern Recognition, Proceedings
Record Number:CaltechAUTHORS:20111209-113314016
Persistent URL:
Official Citation:Weber, M.; Welling, M.; Perona, P.; , "Towards automatic discovery of object categories," Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on , vol.2, no., pp.101-108 vol.2, 2000 doi: 10.1109/CVPR.2000.854754 URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:28398
Deposited By: Ruth Sustaita
Deposited On:09 Dec 2011 21:00
Last Modified:09 Nov 2021 16:56

Repository Staff Only: item control page