Decoding class dynamics in learning with noisy labels
Mostra el registre complet Registre parcial de l'ítem
- dc.contributor.author Tatjer, Albert
- dc.contributor.author Nagarajan, Bhalaji
- dc.contributor.author Marques, Ricardo
- dc.contributor.author Radeva, Petia
- dc.date.accessioned 2025-11-11T07:15:25Z
- dc.date.available 2025-11-11T07:15:25Z
- dc.date.issued 2024
- dc.description.abstract The creation of large-scale datasets annotated by humans inevitably introduces noisy labels, leading to reduced generalization in deep-learning models. Sample selection-based learning with noisy labels is a recent approach that exhibits promising upbeat performance improvements. The selection of clean samples amongst the noisy samples is an important criterion in the learning process of these models. In this work, we delve deeper into the clean-noise split decision and highlight the aspect that effective demarcation of samples would lead to better performance. We identify the Global Noise Conundrum in the existing models, where the distribution of samples is treated globally. We propose a per-class-based local distribution of samples and demonstrate the effectiveness of this approach in having a better clean-noise split. We validate our proposal on several benchmarks — both real and synthetic, and show substantial improvements over different state-of-the-art algorithms. We further propose a new metric, classiness to extend our analysis and highlight the effectiveness of the proposed method. Source code and instructions to reproduce this paper are available at https://github.com/aldakata/CCLM/en
- dc.description.sponsorship This work was partially funded by the 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), CERCA Programme/Generalitat de Catalunya, and Grants PID2022-141566NB-I00 (IDEATE), PDC2022-133642-I00 (DeepFoodVol), and CNS2022-135480 (A-BMC) funded by MICIU/AEI/10.13039/501100011033, by FEDER (UE), and by European Union NextGenerationEU/ PRTR. R. Marques acknowledges the support of the Serra Húnter Programme. B. Nagarajan acknowledges the support of FPI Becas, MICINN, Spain .en
- dc.format.mimetype application/pdf
- dc.identifier.citation Tatjer A, Nagarajan B, Marques R, Radeva P. Decoding class dynamics in learning with noisy labels. Pattern Recognit Lett. 2024 Aug;184:239-45. DOI: 10.1016/j.patrec.2024.04.012
- dc.identifier.doi http://dx.doi.org/10.1016/j.patrec.2024.04.012
- dc.identifier.issn 0167-8655
- dc.identifier.uri http://hdl.handle.net/10230/71851
- dc.language.iso eng
- dc.publisher Elsevier
- dc.relation.ispartof Pattern Recognition Letters. 2024 Aug;184:239-45
- dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/01070421
- dc.relation.projectID info:eu-repo/grantAgreement/ES/3PE/PID2022-141566NB-I00
- dc.relation.projectID info:eu-repo/grantAgreement/ES/3PE/PDC2022-133642-I00
- dc.relation.projectID info:eu-repo/grantAgreement/ES/3PE/CNS2022-135480
- dc.rights © 2024 The Authors. Published by Elsevier B.V. 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 Label noise modellingen
- dc.subject.keyword Class dynamicsen
- dc.title Decoding class dynamics in learning with noisy labelsen
- dc.type info:eu-repo/semantics/article
- dc.type.version info:eu-repo/semantics/publishedVersion