The University of Southampton
University of Southampton Institutional Repository

Revisiting deep fisher vectors: using fisher information to improve object classification

Revisiting deep fisher vectors: using fisher information to improve object classification
Revisiting deep fisher vectors: using fisher information to improve object classification
Although deep learning models have become the gold standard in achieving outstanding results on a large variety of computer vision and machine learning tasks, the use of kernel methods has still not gone out of trend because of its potential to beat deep learning performances at a number of occasions. Given the potential of kernel techniques, prior works have also proposed the use of hybrid approaches combining deep learning with kernel learning to complement their respective strengths and weaknesses. This work develops this idea further by introducing an improved version of Fisher kernels derived from the deep Boltzmann machines (DBM). Our improved deep Fisher kernel (IDFK) utilises an approximation of the Fisher information matrix to derive improved Fisher vectors. We show IDFK can be utilised to retain a high degree of class separability, making it appropriate for classification and retrieval tasks. The efficacy of the proposed approach is evaluated on three benchmark data sets: MNIST, USPS and Alphanumeric, showing an improvement in classification performance over existing kernel approaches, and comparable performance to deep learning methods, but with much reduced computational costs. Using explainable AI methods, we also demonstrate why our IDFK leads to better classification performance.
Ahmed, Sarah
65eca5c3-8a27-437a-a8d0-59401236f39b
Azim, Tayyaba
4e6decad-1e15-4e87-822c-70ca0ac8654a
Early, Joseph Arthur
fd4e9e4c-9251-474d-a9cf-12157a9f2f73
Ramchurn, Sarvapali
1d62ae2a-a498-444e-912d-a6082d3aaea3
Ahmed, Sarah
65eca5c3-8a27-437a-a8d0-59401236f39b
Azim, Tayyaba
4e6decad-1e15-4e87-822c-70ca0ac8654a
Early, Joseph Arthur
fd4e9e4c-9251-474d-a9cf-12157a9f2f73
Ramchurn, Sarvapali
1d62ae2a-a498-444e-912d-a6082d3aaea3

Ahmed, Sarah, Azim, Tayyaba, Early, Joseph Arthur and Ramchurn, Sarvapali (2022) Revisiting deep fisher vectors: using fisher information to improve object classification. British Machine Vision Conference, , London, United Kingdom. 21 - 24 Nov 2022. 10 pp .

Record type: Conference or Workshop Item (Paper)

Abstract

Although deep learning models have become the gold standard in achieving outstanding results on a large variety of computer vision and machine learning tasks, the use of kernel methods has still not gone out of trend because of its potential to beat deep learning performances at a number of occasions. Given the potential of kernel techniques, prior works have also proposed the use of hybrid approaches combining deep learning with kernel learning to complement their respective strengths and weaknesses. This work develops this idea further by introducing an improved version of Fisher kernels derived from the deep Boltzmann machines (DBM). Our improved deep Fisher kernel (IDFK) utilises an approximation of the Fisher information matrix to derive improved Fisher vectors. We show IDFK can be utilised to retain a high degree of class separability, making it appropriate for classification and retrieval tasks. The efficacy of the proposed approach is evaluated on three benchmark data sets: MNIST, USPS and Alphanumeric, showing an improvement in classification performance over existing kernel approaches, and comparable performance to deep learning methods, but with much reduced computational costs. Using explainable AI methods, we also demonstrate why our IDFK leads to better classification performance.

This record has no associated files available for download.

More information

Accepted/In Press date: 1 October 2022
e-pub ahead of print date: 22 November 2022
Published date: 22 November 2022
Venue - Dates: British Machine Vision Conference, , London, United Kingdom, 2022-11-21 - 2022-11-24

Identifiers

Local EPrints ID: 471260
URI: http://eprints.soton.ac.uk/id/eprint/471260
PURE UUID: 7b1683ac-2bbf-4dfb-a61d-9305dd53c05c
ORCID for Sarvapali Ramchurn: ORCID iD orcid.org/0000-0001-9686-4302

Catalogue record

Date deposited: 01 Nov 2022 17:44
Last modified: 12 Aug 2023 01:38

Export record

Contributors

Author: Sarah Ahmed
Author: Tayyaba Azim
Author: Joseph Arthur Early
Author: Sarvapali Ramchurn ORCID iD

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×