Producción CyT
Artículo
Autoría
Zhang, Zhiwen
;
Duan, Feng
;
CAIAFA, CESAR FEDERICO
;
Solé Casals, Jordi
Fecha
2022
Editorial y Lugar de Edición
SPRINGER
Revista
WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS,
vol. 25
SPRINGER
Resumen
Información suministrada por el agente en
SIGEVA
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 anoth...
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.
Ver más
Ver menos
Palabras Clave
transfer learningsaliency mapvisual attention
Descargue o solicite el texto completo