Please use this identifier to cite or link to this item: http://bura.brunel.ac.uk/handle/2438/30314
Full metadata record
DC FieldValueLanguage
dc.contributor.authorXue, Y-
dc.contributor.authorYang, R-
dc.contributor.authorChen, X-
dc.contributor.authorLiu, W-
dc.contributor.authorWang, Z-
dc.contributor.authorLiu, X-
dc.date.accessioned2024-12-04T15:17:43Z-
dc.date.available2024-12-04T15:17:43Z-
dc.date.issued2024-08-19-
dc.identifierORCiD: Weibo Liu https://orcid.org/0000-0002-8169-3261-
dc.identifierORCiD: Zidong Wang https://orcid.org/0000-0002-9576-7401-
dc.identifierORCiD: Xiaohui Liu https://orcid.org/0000-0003-1589-1267-
dc.identifier.citationXue, Y. et al. (2024) 'A Review on Transferability Estimation in Deep Transfer Learning', IEEE Transactions on Artificial Intelligence, 5 (12), pp. 5894 - 5914. doi: 10.1109/TAI.2024.3445892.en_US
dc.identifier.urihttps://bura.brunel.ac.uk/handle/2438/30314-
dc.descriptionImpact Statement: The burgeoning field of deep transfer learning holds significant promise across various industries but encounters challenges in effective implementation. Mitigating negative transfer arising from dissimilarities between the source and target domains is crucial for successful deployment. This review delves into the realm of transferability estimation, a vital aspect in enhancing the efficacy of deep transfer learning approaches. By evaluating the transferability of data and models, these methods play a pivotal role in alleviating negative transfer effects. This review systematically categorizes and qualitatively analyzes four types of prominent transferability estimation methods, offering valuable insights for researchers to judiciously select appropriate methods. The significance of this work lies in guiding researchers in selecting appropriate deep transfer learning methods for different tasks, ensuring optimal performance across varied tasks. Furthermore, this review delineates several open problems in transferability estimation, charting a course for future research endeavors.en_US
dc.description.abstractDeep transfer learning has become increasingly prevalent in various fields such as industry and medical science in recent years. To ensure the successful implementation of target tasks and improve the transfer performance, it is meaningful to prevent negative transfer. However, the dissimilarity between the data from source domain and target domain can pose challenges to transfer learning. Additionally, different transfer models exhibit significant variations in performance for target tasks, potentially leading to a negative transfer phenomenon. To mitigate the adverse effects of the above factors, transferability estimation methods are employed in this field to evaluate the transferability of the data and the models of various deep transfer learning methods. These methods ascertain transferability by incorporating mutual information between the data or models of the source domain and the target domain. This paper furnishes a comprehensive overview of four categories of transferability estimation methods in recent years. It employs qualitative analysis to evaluate various transferability estimation approaches, assisting researchers in selecting appropriate methods. Furthermore, this paper evaluates the open problems associated with transferability estimation methods, proposing potential emerging areas for further research. Lastly, the open-source datasets commonly used in transferability estimation studies are summarized in this study.en_US
dc.description.sponsorshipThis work is partially supported by the Jiangsu Provincial Qinglan Project (2021), the Research Development Fund of XJTLU (RDF-20-01-18) and the Suzhou Science and Technology Programme (SYG202106).en_US
dc.format.extent5894 - 5914-
dc.format.mediumElectronic-
dc.languageEnglish-
dc.language.isoen_USen_US
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.rightsCopyright © 2024 Institute of Electrical and Electronics Engineers (IEEE). Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. See: https://journals.ieeeauthorcenter.ieee.org/become-an-ieee-journal-author/publishing-ethics/guidelines-and-policies/post-publication-policies/-
dc.rights.urihttps://journals.ieeeauthorcenter.ieee.org/become-an-ieee-journal-author/publishing-ethics/guidelines-and-policies/post-publication-policies/-
dc.subjectdeep transfer learningen_US
dc.subjectnegative transferen_US
dc.subjecttransferability estimationen_US
dc.subjecttransfer performance.en_US
dc.titleA Review on Transferability Estimation in Deep Transfer Learningen_US
dc.typeArticleen_US
dc.identifier.doihttps://doi.org/10.1109/TAI.2024.3445892-
dc.relation.isPartOfIEEE Transactions on Artificial Intelligence-
pubs.issue12-
pubs.publication-statusPublished-
pubs.volume5-
dc.identifier.eissn2691-4581-
dc.rights.holderInstitute of Electrical and Electronics Engineers (IEEE)-
Appears in Collections:Dept of Computer Science Research Papers

Files in This Item:
File Description SizeFormat 
FullText.pdfCopyright © 2024 Institute of Electrical and Electronics Engineers (IEEE). Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. See: https://journals.ieeeauthorcenter.ieee.org/become-an-ieee-journal-author/publishing-ethics/guidelines-and-policies/post-publication-policies/3.81 MBAdobe PDFView/Open


Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.