Doing more with less: similarity neural nets and metrics for small class imbalanced data sets

Veal, Charlie, Schulz, Jeffrey, Buck, Andrew, Anderson, Derek, Keller, James, Popescu, Mihail, Scott, Grant, Ho, Dominic and Wilkin, Timothy 2020, Doing more with less: similarity neural nets and metrics for small class imbalanced data sets, in Proceedings of SPIE Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXV, SPIE, Bellingham, Washington, pp. 1141802-1-1141802-12, doi: 10.1117/12.2558092.

Attached Files
Name Description MIMEType Size Downloads

Title Doing more with less: similarity neural nets and metrics for small class imbalanced data sets
Author(s) Veal, Charlie
Schulz, Jeffrey
Buck, Andrew
Anderson, Derek
Keller, James
Popescu, Mihail
Scott, Grant
Ho, Dominic
Wilkin, TimothyORCID iD for Wilkin, Timothy orcid.org/0000-0003-4059-1354
Conference name Society of Photo-Optical Instrumentation Engineers. Conference (2020 : Online Only, United States)
Conference location Online Only, United States
Conference dates 2020/04/27 - 2020/05/08
Title of proceedings Proceedings of SPIE Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXV
Editor(s) Bishop, Steven S
Isaacs, Jason C
Publication date 2020
Series Society of Photo-Optical Instrumentation Engineers Conference
Start page 1141802-1
End page 1141802-12
Total pages 12
Publisher SPIE
Place of publication Bellingham, Washington
Keyword(s) artificial neural network
siamese network
triplet loss
deep learning
explosive hazard detection
automatic target recognition
similarity network
ISBN 9781510636132
ISSN 0277-786X
1996-756X
Language eng
DOI 10.1117/12.2558092
Indigenous content off
HERDC Research category E1 Full written paper - refereed
Persistent URL http://hdl.handle.net/10536/DRO/DU:30140655

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 0 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 31 Abstract Views, 2 File Downloads  -  Detailed Statistics
Created: Thu, 06 Aug 2020, 09:38:05 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.