St Andrews Research Repository

St Andrews University Home
View Item 
  •   St Andrews Research Repository
  • University of St Andrews Research
  • University of St Andrews Research
  • University of St Andrews Research
  • View Item
  •   St Andrews Research Repository
  • University of St Andrews Research
  • University of St Andrews Research
  • University of St Andrews Research
  • View Item
  •   St Andrews Research Repository
  • University of St Andrews Research
  • University of St Andrews Research
  • University of St Andrews Research
  • View Item
  • Register / Login
JavaScript is disabled for your browser. Some features of this site may not work without it.

Baseline fusion for image an pattern recognition - what not to do (and how to do better)

Thumbnail
View/Open
Arandelovic_Baseline_fusion_JImaging_44_CC.pdf (1.517Mb)
Date
12/2017
Author
Arandelovic, Ognjen
Keywords
Prediction
Arrhythmia
Image matching
Object recognition
QA75 Electronic computers. Computer science
T Technology
NDAS
BDC
R2C
~DC~
Metadata
Show full item record
Abstract
The ever-increasing demand for a reliable inference capable of handling unpredictable challenges of practical application in the real world has made research on information fusion of major importance; indeed, this challenge is pervasive in a whole range of image understanding tasks. In the development of the most common type—score-level fusion algorithms—it is virtually universally desirable to have as a reference starting point a simple and universally sound baseline benchmark which newly developed approaches can be compared to. One of the most pervasively used methods is that of weighted linear fusion. It has cemented itself as the default off-the-shelf baseline owing to its simplicity of implementation, interpretability, and surprisingly competitive performance across a widest range of application domains and information source types. In this paper I argue that despite this track record, weighted linear fusion is not a good baseline on the grounds that there is an equally simple and interpretable alternative—namely quadratic mean-based fusion—which is theoretically more principled and which is more successful in practice. I argue the former from first principles and demonstrate the latter using a series of experiments on a diverse set of fusion problems: classification using synthetically generated data, computer vision-based object recognition, arrhythmia detection, and fatality prediction in motor vehicle accidents. On all of the aforementioned problems and in all instances, the proposed fusion approach exhibits superior performance over linear fusion, often increasing class separation by several orders of magnitude.
Citation
Arandelovic , O 2017 , ' Baseline fusion for image an pattern recognition - what not to do (and how to do better) ' , Journal of Imaging , vol. 3 , no. 4 , 44 , pp. 1-16 . https://doi.org/10.3390/jimaging3040044
Publication
Journal of Imaging
Status
Peer reviewed
DOI
https://doi.org/10.3390/jimaging3040044
ISSN
2313-433X
Type
Journal article
Rights
Copyright the Author 2017. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).
Description
(Special issue on Computer Vision and Pattern Recognition).
Collections
  • University of St Andrews Research
URI
http://hdl.handle.net/10023/11856

Items in the St Andrews Research Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

Advanced Search

Browse

All of RepositoryCommunities & CollectionsBy Issue DateNamesTitlesSubjectsClassificationTypeFunderThis CollectionBy Issue DateNamesTitlesSubjectsClassificationTypeFunder

My Account

Login

Open Access

To find out how you can benefit from open access to research, see our library web pages and Open Access blog. For open access help contact: openaccess@st-andrews.ac.uk.

Accessibility

Read our Accessibility statement.

How to submit research papers

The full text of research papers can be submitted to the repository via Pure, the University's research information system. For help see our guide: How to deposit in Pure.

Electronic thesis deposit

Help with deposit.

Repository help

For repository help contact: Digital-Repository@st-andrews.ac.uk.

Give Feedback

Cookie policy

This site may use cookies. Please see Terms and Conditions.

Usage statistics

COUNTER-compliant statistics on downloads from the repository are available from the IRUS-UK Service. Contact us for information.

© University of St Andrews Library

University of St Andrews is a charity registered in Scotland, No SC013532.

  • Facebook
  • Twitter