Aggregating local image descriptors into compact codes - Archive ouverte HAL Access content directly
Journal Articles IEEE Transactions on Pattern Analysis and Machine Intelligence Year : 2012

Aggregating local image descriptors into compact codes

(1) , (2) , (3, 4) , (2) , (5) , (3)
1
2
3
4
5

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.
Fichier principal
Vignette du fichier
jegou_aggregate.pdf (696.72 Ko) Télécharger le fichier
Vignette du fichier
teaser.jpg (15.64 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Loading...

Dates and versions

inria-00633013 , version 1 (17-10-2011)

Identifiers

Cite

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, 2012, 34 (9), pp.1704-1716. ⟨10.1109/TPAMI.2011.235⟩. ⟨inria-00633013⟩
4097 View
17271 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More