Bayesian DivideMix++ for enhanced learning with noisy labels

Leveraging inexpensive and human intervention-based annotating methodologies, such as crowdsourcing and web crawling, often leads to datasets with noisy labels. Noisy labels can have a detrimental impact on the performance and generalization of deep neural networks. Robust models that are able to ha...

ver descrição completa

Detalhes bibliográficos
Autores: Nagarajan, Bhalaji, Marques, Ricardo, Aguilar, Eduardo J., Radeva, Petia
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2024
País:España
Recursos:Universitat Pompeu Fabra
Repositorio:Repositorio Digital de la UPF
OAI Identifier:oai:repositori.upf.edu:10230/71905
Acesso em linha:http://hdl.handle.net/10230/71905
http://dx.doi.org/10.1016/j.neunet.2024.106122
Access Level:acceso abierto
Palavra-chave:Learning with noisy labels
Neural network memorization
Data augmentation
Self-supervised pre-training
Label uncertainty
Monte-Carlo dropouts
id ES_b8bdf4d7c2fbf1f8e5a2cbd1a2dca026
oai_identifier_str oai:repositori.upf.edu:10230/71905
network_acronym_str ES
network_name_str España
repository_id_str
spelling Bayesian DivideMix++ for enhanced learning with noisy labelsNagarajan, BhalajiMarques, RicardoAguilar, Eduardo J.Radeva, PetiaLearning with noisy labelsNeural network memorizationData augmentationSelf-supervised pre-trainingLabel uncertaintyMonte-Carlo dropoutsLeveraging inexpensive and human intervention-based annotating methodologies, such as crowdsourcing and web crawling, often leads to datasets with noisy labels. Noisy labels can have a detrimental impact on the performance and generalization of deep neural networks. Robust models that are able to handle and mitigate the effect of these noisy labels are thus essential. In this work, we explore the open challenges of neural network memorization and uncertainty in creating robust learning algorithms with noisy labels. To overcome them, we propose a novel framework called “Bayesian DivideMix++” with two critical components: (i) DivideMix++, to enhance the robustness against memorization and (ii) Monte-Carlo MixMatch, which focuses on improving the effectiveness towards label uncertainty. DivideMix++ improves the pipeline by integrating the warm-up and augmentation pipeline with self-supervised pre-training and dedicated different data augmentations for loss analysis and backpropagation. Monte-Carlo MixMatch leverages uncertainty measurements to mitigate the influence of uncertain samples by reducing their weight in the data augmentation MixMatch step. We validate our proposed pipeline using four datasets encompassing various synthetic and real-world noise settings. We demonstrate the effectiveness and merits of our proposed pipeline using extensive experiments. Bayesian DivideMix++ outperforms the state-of-the-art models by considerable differences in all experiments. Our findings underscore the potential of leveraging these modifications to enhance the performance and generalization of deep neural networks in practical scenarios.This work was partially funded by the Horizon EU project MUSAE (No. 01070421), 2021-SGR-01094 (AGAUR), Icrea Academia’2022 (Generalitat de Catalunya), Robo STEAM (2022-1-BG01-KA220-VET-000089434, Erasmus＋ EU), DeepSense (ACE053/22/000029, ACCIÓ), DeepFoodVol (AEI-MICINN, PDC2022-133642-I00), IDEATE (AEI-MICINN, PID2022-141566NB-I00), A-BMC (AEI-MICINN, CNS2022-135480), CERCA Programme/Generalitat de Catalunya, and Agencia Nacional de Investigación y Desarrollo de Chile (ANID) (Grant No. FONDECYT INICIACIÓN 11230262). Ricardo Marques acknowledges the support of the Serra Húnter Programme. B. Nagarajan acknowledges the support of FPI Becas, MICINN, Spain . The authors thankfully acknowledge the computer resources at FinisTerrae III and the technical support provided by the Galician Supercomputing Center (CESGA) (RES-IM-2023-2-0025).Elsevier202520252024info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/10230/71905http://dx.doi.org/10.1016/j.neunet.2024.106122reponame:Repositorio Digital de la UPFinstname:Universitat Pompeu FabraInglésNeural Networks. 2024 Apr;172:106122info:eu-repo/grantAgreement/ES/3PE/PDC2022-133642-I00info:eu-repo/grantAgreement/ES/3PE/PID2022-141566NB-I00info:eu-repo/grantAgreement/ES/3PE/CNS2022-135480© 2024 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).http://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:repositori.upf.edu:10230/719052026-06-12T07:21:37Z
dc.title.none.fl_str_mv Bayesian DivideMix++ for enhanced learning with noisy labels
title Bayesian DivideMix++ for enhanced learning with noisy labels
spellingShingle Bayesian DivideMix++ for enhanced learning with noisy labels
Nagarajan, Bhalaji
Learning with noisy labels
Neural network memorization
Data augmentation
Self-supervised pre-training
Label uncertainty
Monte-Carlo dropouts
title_short Bayesian DivideMix++ for enhanced learning with noisy labels
title_full Bayesian DivideMix++ for enhanced learning with noisy labels
title_fullStr Bayesian DivideMix++ for enhanced learning with noisy labels
title_full_unstemmed Bayesian DivideMix++ for enhanced learning with noisy labels
title_sort Bayesian DivideMix++ for enhanced learning with noisy labels
dc.creator.none.fl_str_mv Nagarajan, Bhalaji
Marques, Ricardo
Aguilar, Eduardo J.
Radeva, Petia
author Nagarajan, Bhalaji
author_facet Nagarajan, Bhalaji
Marques, Ricardo
Aguilar, Eduardo J.
Radeva, Petia
author_role author
author2 Marques, Ricardo
Aguilar, Eduardo J.
Radeva, Petia
author2_role author
author
author
dc.subject.none.fl_str_mv Learning with noisy labels
Neural network memorization
Data augmentation
Self-supervised pre-training
Label uncertainty
Monte-Carlo dropouts
topic Learning with noisy labels
Neural network memorization
Data augmentation
Self-supervised pre-training
Label uncertainty
Monte-Carlo dropouts
description Leveraging inexpensive and human intervention-based annotating methodologies, such as crowdsourcing and web crawling, often leads to datasets with noisy labels. Noisy labels can have a detrimental impact on the performance and generalization of deep neural networks. Robust models that are able to handle and mitigate the effect of these noisy labels are thus essential. In this work, we explore the open challenges of neural network memorization and uncertainty in creating robust learning algorithms with noisy labels. To overcome them, we propose a novel framework called “Bayesian DivideMix++” with two critical components: (i) DivideMix++, to enhance the robustness against memorization and (ii) Monte-Carlo MixMatch, which focuses on improving the effectiveness towards label uncertainty. DivideMix++ improves the pipeline by integrating the warm-up and augmentation pipeline with self-supervised pre-training and dedicated different data augmentations for loss analysis and backpropagation. Monte-Carlo MixMatch leverages uncertainty measurements to mitigate the influence of uncertain samples by reducing their weight in the data augmentation MixMatch step. We validate our proposed pipeline using four datasets encompassing various synthetic and real-world noise settings. We demonstrate the effectiveness and merits of our proposed pipeline using extensive experiments. Bayesian DivideMix++ outperforms the state-of-the-art models by considerable differences in all experiments. Our findings underscore the potential of leveraging these modifications to enhance the performance and generalization of deep neural networks in practical scenarios.
publishDate 2024
dc.date.none.fl_str_mv 2024
2025
2025
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10230/71905
http://dx.doi.org/10.1016/j.neunet.2024.106122
url http://hdl.handle.net/10230/71905
http://dx.doi.org/10.1016/j.neunet.2024.106122
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Neural Networks. 2024 Apr;172:106122
info:eu-repo/grantAgreement/ES/3PE/PDC2022-133642-I00
info:eu-repo/grantAgreement/ES/3PE/PID2022-141566NB-I00
info:eu-repo/grantAgreement/ES/3PE/CNS2022-135480
dc.rights.none.fl_str_mv http://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:Repositorio Digital de la UPF
instname:Universitat Pompeu Fabra
instname_str Universitat Pompeu Fabra
reponame_str Repositorio Digital de la UPF
collection Repositorio Digital de la UPF
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869417675205115905
score 15,812455

Registos relacionados