Symmetric cross entropy for robust learning with noisy labels

Wang, Yisen, Ma, Xingjun, Chen, Zaiyi, Luo, Yuan, Yi, Jinfeng and Bailey, James 2019, Symmetric cross entropy for robust learning with noisy labels, in ICCV 2019 : Proceedings of the IEEE/CVF International Conference on Computer Vision, IEEE, Piscataway, N.J., pp. 322-330, doi: 10.1109/iccv.2019.00041.

Attached Files
Name Description MIMEType Size Downloads

Title Symmetric cross entropy for robust learning with noisy labels
Author(s) Wang, Yisen
Ma, XingjunORCID iD for Ma, Xingjun orcid.org/0000-0003-2099-4973
Chen, Zaiyi
Luo, Yuan
Yi, Jinfeng
Bailey, James
Conference name Computer vision. International conference (2019 : Seoul, South Korea)
Conference location Seoul, South Korea
Conference dates 2019/10/27 - 2019/11/02
Title of proceedings ICCV 2019 : Proceedings of the IEEE/CVF International Conference on Computer Vision
Editor(s) [Unknown]
Publication date 2019
Start page 322
End page 330
Total pages 9
Publisher IEEE
Place of publication Piscataway, N.J.
Keyword(s) symmetric cross entropy learning
noise robust counterpart reverse cross entropy
noisy labels
robust learning
DNN learning
RCE
deep neural networks
ISBN 9781728148038
9781728148045
ISSN 1550-5499
2380-7504
Language eng
DOI 10.1109/iccv.2019.00041
Indigenous content off
HERDC Research category E1.1 Full written paper - refereed
Persistent URL http://hdl.handle.net/10536/DRO/DU:30139150

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 1 times in TR Web of Science
Scopus Citation Count Cited 2 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 33 Abstract Views, 1 File Downloads  -  Detailed Statistics
Created: Tue, 16 Jun 2020, 15:12:15 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.