A Caltech Library Service

Weakly supervised scale-invariant learning of models for visual recognition

Fergus, R. and Perona, P. and Zisserman, A. (2007) Weakly supervised scale-invariant learning of models for visual recognition. International Journal of Computer Vision, 71 (3). pp. 273-303. ISSN 0920-5691.

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

Use this Persistent URL to link to this item:


We investigate a method for learning object categories in a weakly supervised manner. Given a set of images known to contain the target category from a similar viewpoint, learning is translation and scale-invariant; does not require alignment or correspondence between the training images, and is robust to clutter and occlusion. Category models are probabilistic constellations of parts, and their parameters are estimated by maximizing the likelihood of the training data. The appearance of the parts, as well as their mutual position, relative scale and probability of detection are explicitly described in the model. Recognition takes place in two stages. First, a feature-finder identifies promising locations for the model's parts. Second, the category model is used to compare the likelihood that the observed features are generated by the category model, or are generated by background clutter. The flexible nature of the model is demonstrated by results over six diverse object categories including geometrically constrained categories (e.g. faces, cars) and flexible objects (such as animals).

Item Type:Article
Related URLs:
URLURL TypeDescription
Perona, P.0000-0002-7583-5809
Additional Information:© 2006 Springer Science + Business Media. First online version published in July, 2006. We are indebted to Li Fei-Fei, David Lowe and Andrew Blake for their insights and suggestions. We also thank Timor Kadir for advice on the feature detector. D. Roth for providing the Cars (Side) dataset. Funding was provided by National Science Foundation Engineering Research Center for Neuromorphic Systems Engineering, the UK EPSRC, EC Project CogViSys and PASCAL Network of Excellence.
Funding AgencyGrant Number
NSF Engineering Research Center for Neuromorphic Systems EngineeringUNSPECIFIED
PASCAL Network of ExcellenceUNSPECIFIED
Subject Keywords:object recognition, parts and structure model, constellation model, semi-supervised learning
Issue or Number:3
Record Number:CaltechAUTHORS:20140730-101717352
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:47599
Deposited By: Caroline Murphy
Deposited On:22 Aug 2014 19:52
Last Modified:03 Oct 2019 06:55

Repository Staff Only: item control page