A Bayesian approach to unsupervised one-shot learning of object categories

Li Fei-Fei, Rob Fergus, Pietro Perona

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Learning visual models of object categories notoriously requires thousands of training examples; this is due to the diversity and richness of object appearance which requires models containing hundreds of parameters. We present a method for learning object categories from just a few images (1 ∼ 5). It is based on incorporating "generic" knowledge which may be obtained from previously learnt models of unrelated categories. We operate in a variational Bayesian framework: object categories are represented by probabilistic models, and "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. Our ideas are demonstrated on four diverse categories (human faces, airplanes, motorcycles, spotted cats). Initially three categories are learnt from hundreds of training examples, and a "prior" is estimated from these. Then the model of the fourth category is learnt from 1 to 5 training examples, and is used for detecting new exemplars a set of test images.

Original languageEnglish (US)
Title of host publicationProceedings of the IEEE International Conference on Computer Vision
Pages1134-1141
Number of pages8
Volume2
StatePublished - 2003
EventNINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION - Nice, France
Duration: Oct 13 2003Oct 16 2003

Other

OtherNINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION
CountryFrance
CityNice
Period10/13/0310/16/03

Fingerprint

Motorcycles
Probability density function
Aircraft
Statistical Models

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Software

Cite this

Fei-Fei, L., Fergus, R., & Perona, P. (2003). A Bayesian approach to unsupervised one-shot learning of object categories. In Proceedings of the IEEE International Conference on Computer Vision (Vol. 2, pp. 1134-1141)

A Bayesian approach to unsupervised one-shot learning of object categories. / Fei-Fei, Li; Fergus, Rob; Perona, Pietro.

Proceedings of the IEEE International Conference on Computer Vision. Vol. 2 2003. p. 1134-1141.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Fei-Fei, L, Fergus, R & Perona, P 2003, A Bayesian approach to unsupervised one-shot learning of object categories. in Proceedings of the IEEE International Conference on Computer Vision. vol. 2, pp. 1134-1141, NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, Nice, France, 10/13/03.
Fei-Fei L, Fergus R, Perona P. A Bayesian approach to unsupervised one-shot learning of object categories. In Proceedings of the IEEE International Conference on Computer Vision. Vol. 2. 2003. p. 1134-1141
Fei-Fei, Li ; Fergus, Rob ; Perona, Pietro. / A Bayesian approach to unsupervised one-shot learning of object categories. Proceedings of the IEEE International Conference on Computer Vision. Vol. 2 2003. pp. 1134-1141
@inproceedings{1ba10a5dd6b94942a44dc622366534ed,
title = "A Bayesian approach to unsupervised one-shot learning of object categories",
abstract = "Learning visual models of object categories notoriously requires thousands of training examples; this is due to the diversity and richness of object appearance which requires models containing hundreds of parameters. We present a method for learning object categories from just a few images (1 ∼ 5). It is based on incorporating {"}generic{"} knowledge which may be obtained from previously learnt models of unrelated categories. We operate in a variational Bayesian framework: object categories are represented by probabilistic models, and {"}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. Our ideas are demonstrated on four diverse categories (human faces, airplanes, motorcycles, spotted cats). Initially three categories are learnt from hundreds of training examples, and a {"}prior{"} is estimated from these. Then the model of the fourth category is learnt from 1 to 5 training examples, and is used for detecting new exemplars a set of test images.",
author = "Li Fei-Fei and Rob Fergus and Pietro Perona",
year = "2003",
language = "English (US)",
volume = "2",
pages = "1134--1141",
booktitle = "Proceedings of the IEEE International Conference on Computer Vision",

}

TY - GEN

T1 - A Bayesian approach to unsupervised one-shot learning of object categories

AU - Fei-Fei, Li

AU - Fergus, Rob

AU - Perona, Pietro

PY - 2003

Y1 - 2003

N2 - Learning visual models of object categories notoriously requires thousands of training examples; this is due to the diversity and richness of object appearance which requires models containing hundreds of parameters. We present a method for learning object categories from just a few images (1 ∼ 5). It is based on incorporating "generic" knowledge which may be obtained from previously learnt models of unrelated categories. We operate in a variational Bayesian framework: object categories are represented by probabilistic models, and "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. Our ideas are demonstrated on four diverse categories (human faces, airplanes, motorcycles, spotted cats). Initially three categories are learnt from hundreds of training examples, and a "prior" is estimated from these. Then the model of the fourth category is learnt from 1 to 5 training examples, and is used for detecting new exemplars a set of test images.

AB - Learning visual models of object categories notoriously requires thousands of training examples; this is due to the diversity and richness of object appearance which requires models containing hundreds of parameters. We present a method for learning object categories from just a few images (1 ∼ 5). It is based on incorporating "generic" knowledge which may be obtained from previously learnt models of unrelated categories. We operate in a variational Bayesian framework: object categories are represented by probabilistic models, and "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. Our ideas are demonstrated on four diverse categories (human faces, airplanes, motorcycles, spotted cats). Initially three categories are learnt from hundreds of training examples, and a "prior" is estimated from these. Then the model of the fourth category is learnt from 1 to 5 training examples, and is used for detecting new exemplars a set of test images.

UR - http://www.scopus.com/inward/record.url?scp=0344983284&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0344983284&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0344983284

VL - 2

SP - 1134

EP - 1141

BT - Proceedings of the IEEE International Conference on Computer Vision

ER -