CMW-Net: an adaptive robust algorithm for sample selection and label correction

A class-aware sample weighting algorithm is developed for general label noise problems. The algorithm can effectively tackle complicated and diverse noisy label tasks, winning the Championship of the ‘Arena Contest’ Track 1 of 2022 Greater BayArea (Huangpu) International Algorithm Case Competition....

Descripción completa

Detalles Bibliográficos
Autores principales: Shu, Jun, Yuan, Xiang, Meng, Deyu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2023
Materias:
PERSPECTIVE
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10246833/
https://www.ncbi.nlm.nih.gov/pubmed/37292084
http://dx.doi.org/10.1093/nsr/nwad084
_version_ 1785055112729722880
author Shu, Jun
Yuan, Xiang
Meng, Deyu
author_facet Shu, Jun
Yuan, Xiang
Meng, Deyu
author_sort Shu, Jun
collection PubMed
description A class-aware sample weighting algorithm is developed for general label noise problems. The algorithm can effectively tackle complicated and diverse noisy label tasks, winning the Championship of the ‘Arena Contest’ Track 1 of 2022 Greater BayArea (Huangpu) International Algorithm Case Competition.
format Online
Article
Text
id pubmed-10246833
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Oxford University Press
record_format MEDLINE/PubMed
spelling pubmed-102468332023-06-08 CMW-Net: an adaptive robust algorithm for sample selection and label correction Shu, Jun Yuan, Xiang Meng, Deyu Natl Sci Rev PERSPECTIVE A class-aware sample weighting algorithm is developed for general label noise problems. The algorithm can effectively tackle complicated and diverse noisy label tasks, winning the Championship of the ‘Arena Contest’ Track 1 of 2022 Greater BayArea (Huangpu) International Algorithm Case Competition. Oxford University Press 2023-03-25 /pmc/articles/PMC10246833/ /pubmed/37292084 http://dx.doi.org/10.1093/nsr/nwad084 Text en © The Author(s) 2023. Published by Oxford University Press on behalf of China Science Publishing & Media Ltd. https://creativecommons.org/licenses/by/4.0/This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle PERSPECTIVE
Shu, Jun
Yuan, Xiang
Meng, Deyu
CMW-Net: an adaptive robust algorithm for sample selection and label correction
title CMW-Net: an adaptive robust algorithm for sample selection and label correction
title_full CMW-Net: an adaptive robust algorithm for sample selection and label correction
title_fullStr CMW-Net: an adaptive robust algorithm for sample selection and label correction
title_full_unstemmed CMW-Net: an adaptive robust algorithm for sample selection and label correction
title_short CMW-Net: an adaptive robust algorithm for sample selection and label correction
title_sort cmw-net: an adaptive robust algorithm for sample selection and label correction
topic PERSPECTIVE
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10246833/
https://www.ncbi.nlm.nih.gov/pubmed/37292084
http://dx.doi.org/10.1093/nsr/nwad084
work_keys_str_mv AT shujun cmwnetanadaptiverobustalgorithmforsampleselectionandlabelcorrection
AT yuanxiang cmwnetanadaptiverobustalgorithmforsampleselectionandlabelcorrection
AT mengdeyu cmwnetanadaptiverobustalgorithmforsampleselectionandlabelcorrection

Ejemplares similares