Aggregating local image descriptors into compact codes

Hervé Jégou 1 Florent Perronnin 2 Matthijs Douze 3, 4 Jorge Sánchez 2 Patrick Pérez 5 Cordelia Schmid 3
1 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
2 Xerox Research Centre Europe [Meylan]
3 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
4 SED [Grenoble]
5 Technicolor R & I [Cesson Sévigné]
Abstract : This paper addresses the problem of large-scale image search. Three constraints have to be taken into account: search accuracy, efficiency, and memory usage. We first present and evaluate different ways of aggregating local image descriptors into a vector and show that the Fisher kernel achieves better performance than the reference bag-of-visual words approach for any given vector dimension. We then jointly optimize dimensionality reduction and indexing in order to obtain a precise vector comparison as well as a compact representation. The evaluation shows that the image representation can be reduced to a few dozen bytes while preserving high accuracy. Searching a 100 million image dataset takes about 250 ms on one processor core.
Keywords : image search image retrieval indexing
Type de document :
Article dans une revue
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2012, 34 (9), pp.1704-1716. 〈10.1109/TPAMI.2011.235〉
Liste complète des métadonnées

Littérature citée [38 références]  Voir  Masquer  Télécharger

teaser.jpg
teaser.jpg
https://hal.inria.fr/inria-00633013
Contributeur : Hervé Jégou <>
Soumis le : lundi 17 octobre 2011 - 14:18:08
Dernière modification le : mercredi 11 avril 2018 - 01:51:28
Document(s) archivé(s) le : jeudi 15 novembre 2012 - 09:50:17

Fichiers

jegou_aggregate.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

INRIA | IRISA | LJK | LJK_GI_LEAR | LJK_GI | UGA | IRISA-D6 | UR1-UFR-ISTIC | UNIV-RENNES | INRIA-RENGRE

Citation

Hervé Jégou, Florent Perronnin, Matthijs Douze, Jorge Sánchez, Patrick Pérez, et al.. Aggregating local image descriptors into compact codes. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2012, 34 (9), pp.1704-1716. 〈10.1109/TPAMI.2011.235〉. 〈inria-00633013〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

4758

Téléchargements de fichiers

13585

Contact


archive-ouverte@inria.fr