International Journal of Computer Vision

, Volume 77, Issue 1–3, pp 219–237

Learning to Recognize Objects with Little Supervision

  • Peter Carbonetto
  • Gyuri Dorkó
  • Cordelia Schmid
  • Hendrik Kück
  • Nando de Freitas
Article

Abstract

This paper shows (i) improvements over state-of-the-art local feature recognition systems, (ii) how to formulate principled models for automatic local feature selection in object class recognition when there is little supervised data, and (iii) how to formulate sensible spatial image context models using a conditional random field for integrating local features and segmentation cues (superpixels). By adopting sparse kernel methods, Bayesian learning techniques and data association with constraints, the proposed model identifies the most relevant sets of local features for recognizing object classes, achieves performance comparable to the fully supervised setting, and obtains excellent results for image classification.

Keywords

Object recognition Scale-invariant keypoints Weakly supervised learning Data association Bayesian analysis Markov Chain Monte Carlo 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  • Peter Carbonetto
    • 1
  • Gyuri Dorkó
    • 2
  • Cordelia Schmid
    • 2
  • Hendrik Kück
    • 1
  • Nando de Freitas
    • 1
  1. 1.University of British ColumbiaVancouverCanada
  2. 2.INRIA Rhône-AlpesGrenobleFrance

Personalised recommendations