| HAL-Inria | Publications, software ... of Inria's scientists |
Aggregating local image descriptors into compact codes
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.
Cited literature [38 references]
https://hal.inria.fr/inria-00633013
Contributor : Hervé Jégou <>
Submitted on : Monday, October 17, 2011 - 2:18:08 PM
Last modification on : Thursday, March 26, 2020 - 8:49:27 PM
Document(s) archivé(s) le : Thursday, November 15, 2012 - 9:50:17 AM
Contributor : Hervé Jégou <>
Submitted on : Monday, October 17, 2011 - 2:18:08 PM
Last modification on : Thursday, March 26, 2020 - 8:49:27 PM
Document(s) archivé(s) le : Thursday, November 15, 2012 - 9:50:17 AM
Files
jegou_aggregate.pdf
Files produced by the author(s)