HAL - INRIA :: [inria-00548668, version 1] Learning to recognize objects with little supervision

inria-00548668, version 1

Learning to recognize objects with little supervision

Peter Carbonetto ¹, Gyuri Dorkó ^2, 3, Cordelia Schmid () ^2, 3, Hendrik Kück ¹, Nando De Freitas ¹

International Journal of Computer Vision 77, 1-3 (2008) 219--238

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.

1: Laboratory for Computational Intelligence (LCI)
University of British Columbia
2: Laboratoire Jean Kuntzmann (LJK)
CNRS : UMR5224 – Université Joseph Fourier - Grenoble I – Université Pierre Mendès-France - Grenoble II – Institut Polytechnique de Grenoble - Grenoble Institute of Technology
3: LEAR (INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann)
CNRS : FR71 – CNRS : UMR5527 – INRIA – Laboratoire Jean Kuntzmann – Université Joseph Fourier - Grenoble I – Institut National Polytechnique de Grenoble (INPG)

inria-00548668, version 1
http://hal.inria.fr/inria-00548668
oai:hal.inria.fr:inria-00548668
From: Team Lear <>
Submitted for: Laure BENAC <>
Submitted on: Monday, 20 December 2010 10:25:44
Updated on: Thursday, 6 January 2011 15:13:59

See detailed view

Associated documents

DOI: 10.1007/s11263-007-0067-7

Full text from publisher

Export

Bibtex EndNote TEI RefWorks

<?xml version="1.0" encoding="UTF-8"?>
<listBibl xmlns="http://www.tei-c.org/ns/1.0" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML">
<listBibl type="article"><head>Articles in peer-reviewed journal</head>
<biblStruct type="article" xml:id="inria-00548668"><analytic>
<author><persName><forename>Peter</forename><surname>Carbonetto</surname></persName>
<affiliation>
<orgName type="laboratory">LCI</orgName>
<orgName type="team">Laboratory for Computational Intelligence</orgName>
<country>CA</country>
<orgName type="institution">University of British Columbia</orgName>
</affiliation>
</author>
<author><persName><forename>Gyuri</forename><surname>Dorkó</surname></persName>
<affiliation>
<orgName type="laboratory">LJK</orgName>
<orgName type="team">Laboratoire Jean Kuntzmann</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR5224</orgName>
<orgName type="institution">Université Joseph Fourier - Grenoble I</orgName>
<orgName type="institution">Université Pierre Mendès-France - Grenoble II</orgName>
<orgName type="institution">Institut Polytechnique de Grenoble - Grenoble Institute of Technology</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann</orgName>
<orgName type="team">LEAR</orgName>
<country>FR</country>
<orgName type="institution">CNRS : FR71</orgName>
<orgName type="institution">CNRS : UMR5527</orgName>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">Laboratoire Jean Kuntzmann</orgName>
<orgName type="institution">Université Joseph Fourier - Grenoble I</orgName>
<orgName type="institution">Institut National Polytechnique de Grenoble (INPG)</orgName>
</affiliation>
</author>
<author><persName><forename>Cordelia</forename><surname>Schmid</surname></persName>
<affiliation>
<orgName type="laboratory">LJK</orgName>
<orgName type="team">Laboratoire Jean Kuntzmann</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR5224</orgName>
<orgName type="institution">Université Joseph Fourier - Grenoble I</orgName>
<orgName type="institution">Université Pierre Mendès-France - Grenoble II</orgName>
<orgName type="institution">Institut Polytechnique de Grenoble - Grenoble Institute of Technology</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann</orgName>
<orgName type="team">LEAR</orgName>
<country>FR</country>
<orgName type="institution">CNRS : FR71</orgName>
<orgName type="institution">CNRS : UMR5527</orgName>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">Laboratoire Jean Kuntzmann</orgName>
<orgName type="institution">Université Joseph Fourier - Grenoble I</orgName>
<orgName type="institution">Institut National Polytechnique de Grenoble (INPG)</orgName>
</affiliation>
</author>
<author><persName><forename>Hendrik</forename><surname>Kück</surname></persName>
<affiliation>
<orgName type="laboratory">LCI</orgName>
<orgName type="team">Laboratory for Computational Intelligence</orgName>
<country>CA</country>
<orgName type="institution">University of British Columbia</orgName>
</affiliation>
</author>
<author><persName><forename>Nando</forename><surname>De Freitas</surname></persName>
<affiliation>
<orgName type="laboratory">LCI</orgName>
<orgName type="team">Laboratory for Computational Intelligence</orgName>
<country>CA</country>
<orgName type="institution">University of British Columbia</orgName>
</affiliation>
</author>
<title type="main" level="a">Learning to recognize objects with little supervision</title></analytic><monogr><title level="j" type="main">International Journal of Computer Vision</title><imprint><publisher>Springer-Verlag</publisher><biblScope type="publicationDate">2008-00-00</biblScope><biblScope type="vol">77</biblScope><biblScope type="issue">1-3</biblScope><biblScope type="pp">219--238</biblScope></imprint></monogr><idno type="doi">10.1007/s11263-007-0067-7</idno><idno type="HALid">http://hal.inria.fr/inria-00548668</idno></biblStruct>
</listBibl>
</listBibl>

Learning to recognize objects with little supervision

Associated documents

See also

Export