Mostrar el registro sencillo del ítem
dc.contributor.author
Zhang, Zhiwen
dc.contributor.author
Duan, Feng
dc.contributor.author
Caiafa, César Federico
![Se ha confirmado la validez de este valor de autoridad por un usuario](/themes/CONICETDigital/images/authority_control/invisible.gif)
dc.contributor.author
Solé Casals, Jordi
dc.date.available
2022-08-08T14:52:40Z
dc.date.issued
2022-04
dc.identifier.citation
Zhang, Zhiwen; Duan, Feng; Caiafa, César Federico; Solé Casals, Jordi; Domain classifier-based transfer learning for visual attention prediction; Springer; World Wide Web-internet And Web Information Systems; 25; 4-2022; 1685–1701
dc.identifier.issn
1386-145X
dc.identifier.uri
http://hdl.handle.net/11336/164548
dc.description.abstract
Benefitting from machine learning techniques based on deep neural networks, data-driven saliency has achieved significant success over the past few decades. However, existing data-hungry models for saliency prediction require large-scale datasets to be trained. Although some studies based on the transfer learning strategy have managed to acquire sufficient information from the limited samples of the target domain, obtaining saliency maps for the transfer process from one image category to another still remains a challenge. To solve this problem, we propose a domain classifier paradigm-based adaptation method for saliency prediction. The method provides sufficient information by classifying the domain from which the data sample originated. Specifically, only a few target domain samples are used in our few-shot transfer learning paradigm, and the prediction results are compared with those obtained through state-of-the-art methods (such as the fine-tuned transfer strategy). To the best of our knowledge, the proposed transfer framework is the first work that conducts saliency prediction while taking the domain adaptation of different image categories into consideration. Comprehensive experiments are conducted on various image category pairs for source and target domains. The experimental results show that our proposed approach achieves a significant performance improvement with respect to conventional transfer learning approaches.
dc.format
application/pdf
dc.language.iso
eng
dc.publisher
Springer
![Se ha confirmado la validez de este valor de autoridad por un usuario](/themes/CONICETDigital/images/authority_control/invisible.gif)
dc.rights
info:eu-repo/semantics/restrictedAccess
dc.rights.uri
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.subject
saliency map
dc.subject
transfer learning
dc.subject
visual attention
dc.subject.classification
Otras Ciencias de la Computación e Información
![Se ha confirmado la validez de este valor de autoridad por un usuario](/themes/CONICETDigital/images/authority_control/invisible.gif)
dc.subject.classification
Ciencias de la Computación e Información
![Se ha confirmado la validez de este valor de autoridad por un usuario](/themes/CONICETDigital/images/authority_control/invisible.gif)
dc.subject.classification
CIENCIAS NATURALES Y EXACTAS
![Se ha confirmado la validez de este valor de autoridad por un usuario](/themes/CONICETDigital/images/authority_control/invisible.gif)
dc.title
Domain classifier-based transfer learning for visual attention prediction
dc.type
info:eu-repo/semantics/article
dc.type
info:ar-repo/semantics/artículo
dc.type
info:eu-repo/semantics/publishedVersion
dc.date.updated
2022-07-04T19:40:59Z
dc.journal.volume
25
dc.journal.pagination
1685–1701
dc.journal.pais
Alemania
![Se ha confirmado la validez de este valor de autoridad por un usuario](/themes/CONICETDigital/images/authority_control/invisible.gif)
dc.description.fil
Fil: Zhang, Zhiwen. Nankai University. College of Artificial Intelligence; China
dc.description.fil
Fil: Duan, Feng. Nankai University. College of Artificial Intelligence; China
dc.description.fil
Fil: Caiafa, César Federico. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Instituto Argentino de Radioastronomía. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto Argentino de Radioastronomía; Argentina
dc.description.fil
Fil: Solé Casals, Jordi. Nankai University. College of Artificial Intelligence; China
dc.journal.title
World Wide Web-internet And Web Information Systems
![Se ha confirmado la validez de este valor de autoridad por un usuario](/themes/CONICETDigital/images/authority_control/invisible.gif)
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/url/https://link.springer.com/10.1007/s11280-022-01027-0
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/doi/http://dx.doi.org/10.1007/s11280-022-01027-0
Archivos asociados