Skip to Main content Skip to Navigation
Book sections

A semi-supervised learning approach to object recognition with spatial integration of local features and segmentation cues

Peter Carbonetto 1 Gyuri Dorkó 2 Cordelia Schmid 2, * Hendrik Kück 1 Nando de Freitas 1
* Corresponding author
2 LEAR - Learning and recognition in vision
GRAVIR - IMAG - Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : This chapter presents a principled way of formulating models for automatic local feature selection in object class recognition when there is little supervised data. Moreover, it discusses how one could formulate sensible spatial image context models using a conditional random field for integrating local features and segmentation cues (superpixels). By adopting sparse kernel methods and Bayesian model selection and data association, the proposed model identifies the most relevant sets of local features for recognizing object classes, achieves performance comparable to the fully supervised setting, and consistently outperforms existing methods for image classification.
Complete list of metadata

https://hal.inria.fr/inria-00548613
Contributor : Thoth Team <>
Submitted on : Monday, December 20, 2010 - 10:07:11 AM
Last modification on : Monday, December 28, 2020 - 3:44:02 PM

Links full text

Identifiers

Collections

IMAG | CNRS | INRIA | UGA

Citation

Peter Carbonetto, Gyuri Dorkó, Cordelia Schmid, Hendrik Kück, Nando de Freitas. A semi-supervised learning approach to object recognition with spatial integration of local features and segmentation cues. Jean Ponce and Martial Hebert and Cordelia Schmid and Andrew Zisserman. Towards category-level object recognition, 4170, Springer, pp.277--300, 2006, Lecture Notes in Computer Science (LNCS), 978-3-540-68794-8. ⟨10.1007/11957959_15⟩. ⟨inria-00548613⟩

Share

Metrics

Record views

310