Aggregating Local Image Descriptors into Compact Codes
Lists
Only you see this
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 data set takes about 250 ms on one processor core.
BibTeX
@article{jegou2012aggregating,
author = {Hervé Jégou and Florent Perronnin and Matthijs Douze and Jorge Sánchez and Patrick Pérez and Cordelia Schmid},
title = {{Aggregating Local Image Descriptors into Compact Codes}},
journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
year = {2012},
url = {https://openreview.net/forum?id=C0arldDwmv},
}Loading related content...