Compression Techniques for Deep Fisher Vectors

Sarah Ahmed, Tayyaba Azim

2017

Abstract

This paper investigates the use of efficient compression techniques for Fisher vectors derived from deep architectures such as Restricted Boltzmann machine (RBM). Fisher representations have recently created a surge of interest by proving their worth for large scale object recognition and retrieval problems, however they suffer from the problem of large dimensionality as well as have some intrinsic properties that make them unique from the conventional bag of visual words (BoW) features. We have shown empirically which of the normalisation and state of the art compression techniques is well suited for deep Fisher vectors making them amenable for large scale visual retrieval with reduced memory footprint. We further show that the compressed Fisher vectors give impressive classification results even with costless linear classifiers like k-nearest neighbour.

Paper Citation

in Harvard Style

Ahmed S. and Azim T. (2017). Compression Techniques for Deep Fisher Vectors . In Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-222-6, pages 217-224. DOI: 10.5220/0006205002170224

in Bibtex Style

@conference{icpram17,
author={Sarah Ahmed and Tayyaba Azim},
title={Compression Techniques for Deep Fisher Vectors},
booktitle={Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2017},
pages={217-224},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006205002170224},
isbn={978-989-758-222-6},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Compression Techniques for Deep Fisher Vectors
SN - 978-989-758-222-6
AU - Ahmed S.
AU - Azim T.
PY - 2017
SP - 217
EP - 224
DO - 10.5220/0006205002170224