File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TKDE.2020.3014697
- Scopus: eid_2-s2.0-85099507851
- WOS: WOS:000789003800020
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Iterative Refinement for Multi-source Visual Domain Adaptation
Title | Iterative Refinement for Multi-source Visual Domain Adaptation |
---|---|
Authors | |
Keywords | Domain Adaptation Multiple Sources Optimal Transport Feature Selection |
Issue Date | 2020 |
Publisher | Institute of Electrical and Electronics Engineers . The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp/?punumber=69 |
Citation | IEEE Transactions on Knowledge and Data Engineering, 2020, Epub 2020-08-06 How to Cite? |
Abstract | One of the main challenges in multi-source domain adaptation is how to reduce the domain discrepancy between each source domain and a target domain, and then evaluate the domain relevance to determine how much knowledge should be transferred from different source domains to the target domain. However, most prior approaches barely consider both discrepancies and relevance among domains. In this paper, we propose an algorithm, called Iterative Refinement based on Feature Selection and the Wasserstein distance (IRFSW), to solve semi-supervised domain adaptation with multiple sources. Specifically, IRFSW aims to explore both the discrepancies and relevance among domains in an iterative learning procedure, which gradually refines the learning performance until the algorithm stops. In each iteration, for each source domain and the target domain, we develop a sparse model to select features in which the domain discrepancy and training loss are reduced simultaneously. Then a classifier is constructed with the selected features of the source and labeled target data. After that, we exploit optimal transport over the selected features to calculate the transferred weights. The weight values are taken as the ensemble weights to combine the learned classifiers to control the amount of knowledge transferred from source domains to the target domain. Experimental results validate the effectiveness of the proposed method. |
Persistent Identifier | http://hdl.handle.net/10722/294082 |
ISSN | 2023 Impact Factor: 8.9 2023 SCImago Journal Rankings: 2.867 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wu, H | - |
dc.contributor.author | Yan, Y | - |
dc.contributor.author | Lin, G | - |
dc.contributor.author | Yang, M | - |
dc.contributor.author | Ng, MKP | - |
dc.contributor.author | Wu, Q | - |
dc.date.accessioned | 2020-11-23T08:26:04Z | - |
dc.date.available | 2020-11-23T08:26:04Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | IEEE Transactions on Knowledge and Data Engineering, 2020, Epub 2020-08-06 | - |
dc.identifier.issn | 1041-4347 | - |
dc.identifier.uri | http://hdl.handle.net/10722/294082 | - |
dc.description.abstract | One of the main challenges in multi-source domain adaptation is how to reduce the domain discrepancy between each source domain and a target domain, and then evaluate the domain relevance to determine how much knowledge should be transferred from different source domains to the target domain. However, most prior approaches barely consider both discrepancies and relevance among domains. In this paper, we propose an algorithm, called Iterative Refinement based on Feature Selection and the Wasserstein distance (IRFSW), to solve semi-supervised domain adaptation with multiple sources. Specifically, IRFSW aims to explore both the discrepancies and relevance among domains in an iterative learning procedure, which gradually refines the learning performance until the algorithm stops. In each iteration, for each source domain and the target domain, we develop a sparse model to select features in which the domain discrepancy and training loss are reduced simultaneously. Then a classifier is constructed with the selected features of the source and labeled target data. After that, we exploit optimal transport over the selected features to calculate the transferred weights. The weight values are taken as the ensemble weights to combine the learned classifiers to control the amount of knowledge transferred from source domains to the target domain. Experimental results validate the effectiveness of the proposed method. | - |
dc.language | eng | - |
dc.publisher | Institute of Electrical and Electronics Engineers . The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp/?punumber=69 | - |
dc.relation.ispartof | IEEE Transactions on Knowledge and Data Engineering | - |
dc.rights | IEEE Transactions on Knowledge and Data Engineering. Copyright © Institute of Electrical and Electronics Engineers . | - |
dc.rights | ©20xx 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. | - |
dc.subject | Domain Adaptation | - |
dc.subject | Multiple Sources | - |
dc.subject | Optimal Transport | - |
dc.subject | Feature Selection | - |
dc.title | Iterative Refinement for Multi-source Visual Domain Adaptation | - |
dc.type | Article | - |
dc.identifier.email | Yan, Y: ygyan@hku.hk | - |
dc.identifier.email | Ng, MKP: michael.ng@hku.hk | - |
dc.identifier.authority | Ng, MKP=rp02578 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TKDE.2020.3014697 | - |
dc.identifier.scopus | eid_2-s2.0-85099507851 | - |
dc.identifier.hkuros | 319015 | - |
dc.identifier.volume | Epub 2020-08-06 | - |
dc.identifier.isi | WOS:000789003800020 | - |
dc.publisher.place | United States | - |