Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories

Li Fei-Fei, Robert Fergus, Pietro Perona

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

Abstract

Current computational approaches to learning visual object categories require thousands of training images, are slow, cannot learn in an incremental manner and cannot incorporate prior information into the learning process. In addition, no algorithm presented in the literature has been tested on more than a handful of object categories. We present an method for learning object categories from just a few training images. It is quick and it uses prior information in a principled way. We test it on a dataset composed of images of objects belonging to 101 widely varied categories. Our proposed method is based on making use of prior information, assembled from (unrelated) object categories which were previously learnt. A generative probabilistic model is used, which represents the shape and appearance of a constellation of features belonging to the object. The parameters of the model are learnt incrementally in a Bayesian manner. Our incremental algorithm is compared experimentally to an earlier batch Bayesian algorithm, as well as to one based on maximum-likelihood. The incremental and batch versions have comparable classification performance on small training sets, but incremental learning is significantly faster, making real-time learning feasible. Both Bayesian methods outperform maximum likelihood on small training sets.

Original languageEnglish (US)
Title of host publicationIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
PublisherIEEE Computer Society
Volume2004-January
EditionJanuary
DOIs
Publication statusPublished - 2004
Event2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2004 - Washington, United States
Duration: Jun 27 2004Jul 2 2004

Other

Other2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2004
CountryUnited States
CityWashington
Period6/27/047/2/04

    Fingerprint

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Fei-Fei, L., Fergus, R., & Perona, P. (2004). Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (January ed., Vol. 2004-January). [1384978] IEEE Computer Society. https://doi.org/10.1109/CVPR.2004.383