HAL - INRIA :: [inria-00548637, version 1] Aggregating local descriptors into a compact image representation

inria-00548637, version 1

Aggregating local descriptors into a compact image representation

Hervé Jégou ()^a^, 1, Matthijs Douze ()^a^, 2, 3, Cordelia Schmid () ^2, 3, Patrick Pérez ()^a^, 4

23rd IEEE Conference on Computer Vision & Pattern Recognition (CVPR '10) (2010) 3304--3311

Abstract: We address the problem of image search on a very large scale, where three constraints have to be considered jointly: the accuracy of the search, its efficiency, and the memory usage of the representation. We first propose a simple yet efficient way of aggregating local image descriptors into a vector of limited dimension, which can be viewed as a simplification of the Fisher kernel representation. We then show how to jointly optimize the dimension reduction and the indexing algorithm, so that it best preserves the quality of vector comparison. The evaluation shows that our approach significantly outperforms the state of the art: the search accuracy is comparable to the bag-of-features approach for an image representation that fits in 20 bytes. Searching a 10 million image dataset takes about 50ms.

a – INRIA
1: TEXMEX (INRIA - IRISA)
CNRS : UMR6074 – INRIA – INSA Rennes – Université de Rennes 1
2: 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)
3: 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
4: Technicolor R & I
Technicolor

inria-00548637, version 1
http://hal.inria.fr/inria-00548637
oai:hal.inria.fr:inria-00548637
From: Hervé Jégou <>
Submitted for: Laure BENAC <>
Submitted on: Monday, 20 December 2010 10:23:05
Updated on: Monday, 10 January 2011 14:59:53

See detailed view

Associated documents

PDF :

Annexes :

DOI: 10.1109/CVPR.2010.5540039

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="inproceedings"><head>Peer-reviewed conferences/proceedings</head>
<biblStruct type="inproceedings" xml:id="inria-00548637"><analytic>
<author><persName><forename>Hervé</forename><surname>Jégou</surname></persName>
<affiliation>
<orgName type="laboratory">INRIA - IRISA</orgName>
<orgName type="team">TEXMEX</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR6074</orgName>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">INSA Rennes</orgName>
<orgName type="institution">Université de Rennes 1</orgName>
</affiliation>
</author>
<author><persName><forename>Matthijs</forename><surname>Douze</surname></persName>
<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>
<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>
</author>
<author><persName><forename>Cordelia</forename><surname>Schmid</surname></persName>
<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>
<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>
</author>
<author><persName><forename>Patrick</forename><surname>Pérez</surname></persName>
<affiliation>
<orgName type="team">Technicolor R & I</orgName>
<country>FR</country>
<orgName type="institution">Technicolor</orgName>
</affiliation>
</author>
<title type="main" level="a">Aggregating local descriptors into a compact image representation</title></analytic><monogr><meeting>23rd IEEE Conference on Computer Vision & Pattern Recognition (CVPR '10)</meeting><imprint><publisher>IEEE Computer Society</publisher><pubPlace><settlement>San Francisco</settlement><country>United States</country></pubPlace><biblScope type="publicationDate">2010-00-00</biblScope><biblScope type="pp">3304--3311</biblScope></imprint></monogr><idno type="doi">10.1109/CVPR.2010.5540039</idno><idno type="HALid">http://hal.inria.fr/inria-00548637</idno><idno type="HALFile">http://hal.inria.fr/inria-00548637/PDF/jegou_compactimagerepresentation.pdf</idno></biblStruct>
</listBibl>
</listBibl>

Aggregating local descriptors into a compact image representation

Associated documents

See also

Export