Aggregating local descriptors into a compact image representation

Hervé Jégou 1 Matthijs Douze 2 Cordelia Schmid 2 Patrick Pérez 3
1 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
2 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
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.
Type de document :
Communication dans un congrès
CVPR 2010 - 23rd IEEE Conference on Computer Vision & Pattern Recognition, Jun 2010, San Francisco, United States. IEEE Computer Society, pp.3304-3311, 2010, <http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5540039>. <10.1109/CVPR.2010.5540039>
Liste complète des métadonnées


https://hal.inria.fr/inria-00548637
Contributeur : Hervé Jégou <>
Soumis le : lundi 20 décembre 2010 - 10:23:05
Dernière modification le : vendredi 13 janvier 2017 - 14:21:09
Document(s) archivé(s) le : lundi 21 mars 2011 - 03:26:15

Identifiants

Citation

Hervé Jégou, Matthijs Douze, Cordelia Schmid, Patrick Pérez. Aggregating local descriptors into a compact image representation. CVPR 2010 - 23rd IEEE Conference on Computer Vision & Pattern Recognition, Jun 2010, San Francisco, United States. IEEE Computer Society, pp.3304-3311, 2010, <http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5540039>. <10.1109/CVPR.2010.5540039>. <inria-00548637>

Partager

Métriques

Consultations de
la notice

982

Téléchargements du document

3226