Bayesian DivideMix++ for enhanced learning with noisy labels

Mostra el registre complet Registre parcial de l'ítem

  • dc.contributor.author Nagarajan, Bhalaji
  • dc.contributor.author Marques, Ricardo
  • dc.contributor.author Aguilar, Eduardo J.
  • dc.contributor.author Radeva, Petia
  • dc.date.accessioned 2025-11-18T06:39:59Z
  • dc.date.available 2025-11-18T06:39:59Z
  • dc.date.issued 2024
  • dc.description.abstract 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.en
  • dc.description.sponsorship 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).en
  • dc.format.mimetype application/pdf
  • dc.identifier.citation Nagarajan B, Marques R, Aguilar E, Radeva P. Bayesian DivideMix++ for enhanced learning with noisy labels. Neural Netw. 2024 Apr;172:106122. DOI: 10.1016/j.neunet.2024.106122
  • dc.identifier.doi http://dx.doi.org/10.1016/j.neunet.2024.106122
  • dc.identifier.issn 0893-6080
  • dc.identifier.uri http://hdl.handle.net/10230/71905
  • dc.language.iso eng
  • dc.publisher Elsevier
  • dc.relation.ispartof Neural Networks. 2024 Apr;172:106122
  • dc.relation.projectID info:eu-repo/grantAgreement/ES/3PE/PDC2022-133642-I00
  • dc.relation.projectID info:eu-repo/grantAgreement/ES/3PE/PID2022-141566NB-I00
  • dc.relation.projectID info:eu-repo/grantAgreement/ES/3PE/CNS2022-135480
  • dc.rights © 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/).
  • dc.rights.accessRights info:eu-repo/semantics/openAccess
  • dc.rights.uri http://creativecommons.org/licenses/by/4.0/
  • dc.subject.keyword Learning with noisy labelsen
  • dc.subject.keyword Neural network memorizationen
  • dc.subject.keyword Data augmentationen
  • dc.subject.keyword Self-supervised pre-trainingen
  • dc.subject.keyword Label uncertaintyen
  • dc.subject.keyword Monte-Carlo dropoutsen
  • dc.title Bayesian DivideMix++ for enhanced learning with noisy labelsen
  • dc.type info:eu-repo/semantics/article
  • dc.type.version info:eu-repo/semantics/publishedVersion

Col·leccions

Articles (Departament de Tecnologies de la Informació i les Comunicacions)