The University of Southampton
University of Southampton Institutional Repository

Description and evaluation of techniques for transfer learning across sub-categories

Description and evaluation of techniques for transfer learning across sub-categories
Description and evaluation of techniques for transfer learning across sub-categories
This report presents contributions in sub-categorisation. In the first part we propose a simple approach to build a meta-learner on individual classifier that is supposed to implicitly learn class inter-dependencies. We further study how the performance is modified if we add automatically learned meta-classes (group of similar classes). In the second part, we address the problem using a structured learning approach. The main idea is to build a graphical model which efficiently performs labelling at multiple levels simultaneously.
s.n.
de Campos, Teófilo
5a114727-e965-47f6-bb67-fae042e0b9fe
Csurka, Gabriela
5f7749c9-4cbf-4611-806d-51b6f9a01793
Perronnin, Florent
96bc8a08-a10a-432d-b0ce-50b07012df06
McAuley, Julian
a399207a-6fd7-462e-b5d4-189d09e4d5c4
Antenreiter, Martin
a1878533-2324-4209-b9f2-de3a95ebfdcb
Ortner, Ronald
c0e5ff80-ad78-48c2-8534-7d3ff7255062
Auer, Peter
4bca3917-b1c7-42e9-b0bb-3c6e99d93d0f
Viitaniemi, Ville
7c404a77-8cc6-410c-a212-2c4fc6e9c7ce
Laaksonen, Jorma
7797e99b-1252-4bf2-9b61-b79e281207fe
Pasupa, Kitsuchart
952ededb-8c97-41b7-a65b-6aba31de2669
Saunders, Craig
26634635-4d4d-4469-b9ec-1d68788aa47a
Hussain, Zakria
88b38b90-5d11-4ab2-9246-a66485deb104
Shawe-Taylor, John
b1931d97-fdd0-4bc1-89bc-ec01648e928b
de Campos, Teófilo
5a114727-e965-47f6-bb67-fae042e0b9fe
Csurka, Gabriela
5f7749c9-4cbf-4611-806d-51b6f9a01793
Perronnin, Florent
96bc8a08-a10a-432d-b0ce-50b07012df06
McAuley, Julian
a399207a-6fd7-462e-b5d4-189d09e4d5c4
Antenreiter, Martin
a1878533-2324-4209-b9f2-de3a95ebfdcb
Ortner, Ronald
c0e5ff80-ad78-48c2-8534-7d3ff7255062
Auer, Peter
4bca3917-b1c7-42e9-b0bb-3c6e99d93d0f
Viitaniemi, Ville
7c404a77-8cc6-410c-a212-2c4fc6e9c7ce
Laaksonen, Jorma
7797e99b-1252-4bf2-9b61-b79e281207fe
Pasupa, Kitsuchart
952ededb-8c97-41b7-a65b-6aba31de2669
Saunders, Craig
26634635-4d4d-4469-b9ec-1d68788aa47a
Hussain, Zakria
88b38b90-5d11-4ab2-9246-a66485deb104
Shawe-Taylor, John
b1931d97-fdd0-4bc1-89bc-ec01648e928b

de Campos, Teófilo, Csurka, Gabriela, Perronnin, Florent, McAuley, Julian, Antenreiter, Martin, Ortner, Ronald, Auer, Peter, Viitaniemi, Ville, Laaksonen, Jorma, Pasupa, Kitsuchart, Saunders, Craig, Hussain, Zakria and Shawe-Taylor, John (2009) Description and evaluation of techniques for transfer learning across sub-categories s.n. ,

Record type: Monograph (Project Report)

Abstract

This report presents contributions in sub-categorisation. In the first part we propose a simple approach to build a meta-learner on individual classifier that is supposed to implicitly learn class inter-dependencies. We further study how the performance is modified if we add automatically learned meta-classes (group of similar classes). In the second part, we address the problem using a structured learning approach. The main idea is to build a graphical model which efficiently performs labelling at multiple levels simultaneously.

PDF pinview-d6-3-final.pdf - Version of Record
Download (4MB)

More information

Published date: 13 October 2009
Organisations: Electronics & Computer Science

Identifiers

Local EPrints ID: 268318
URI: https://eprints.soton.ac.uk/id/eprint/268318
PURE UUID: fe5c6187-090f-4817-94a2-c52ed006febe

Catalogue record

Date deposited: 15 Dec 2009 13:57
Last modified: 18 Jul 2017 06:55

Export record

Contributors

Author: Teófilo de Campos
Author: Gabriela Csurka
Author: Florent Perronnin
Author: Julian McAuley
Author: Martin Antenreiter
Author: Ronald Ortner
Author: Peter Auer
Author: Ville Viitaniemi
Author: Jorma Laaksonen
Author: Kitsuchart Pasupa
Author: Craig Saunders
Author: Zakria Hussain
Author: John Shawe-Taylor

University divisions

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 https://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.

×