Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published April 2006 | Published
Journal Article Open

One-shot learning of object categories

Abstract

Learning visual models of object categories notoriously requires hundreds or thousands of training examples. We show that it is possible to learn much information about a category from just one, or a handful, of images. The key insight is that, rather than learning from scratch, one can take advantage of knowledge coming from previously learned categories, no matter how different these categories might be. We explore a Bayesian implementation of this idea. Object categories are represented by probabilistic models. Prior knowledge is represented as a probability density function on the parameters of these models. The posterior model for an object category is obtained by updating the prior in the light of one or more observations. We test a simple implementation of our algorithm on a database of 101 diverse object categories. We compare category models learned by an implementation of our Bayesian approach to models learned from by maximum likelihood (ML) and maximum a posteriori (MAP) methods. We find that on a database of more than 100 categories, the Bayesian approach produces informative models when the number of training examples is too small for other methods to operate successfully.

Additional Information

© 2006 IEEE Manuscript received 30 Aug. 2004; revised 12 July 2005; accepted 12 July 2005; published online 14 Feb. 2006. [Posted online: 2006-02-21] Recommended for acceptance by R. Basri. The authors would like to thank Andrew Zisserman, David Mackay, Brian Ripley, and Joel Lindop. This work was supported by the Caltech CNSE, the UK EPSRC, and EC Project CogViSys.

Attached Files

Published - LIFieeetpam06.pdf

Files

LIFieeetpam06.pdf
Files (6.2 MB)
Name Size Download all
md5:7c25b159b9cebdb4d9edb36b3c1ed7ff
6.2 MB Preview Download

Additional details

Created:
August 22, 2023
Modified:
October 16, 2023