Salient object detection via multi-scale attention CNN

Fully convolutional network (FCN) based semantic segmentation models have largely inspired most recent works in the field of salient object detection. However, the lack of context information summarization can degrade the prediction accuracy of the final saliency map. Moreover, the information loss...

Full description

Bibliographic Details

Published in:	Neurocomputing (Amsterdam) Vol. 322; pp. 130 - 140
Main Authors:	Ji, Yuzhu, Zhang, Haijun, Jonathan Wu, Q.M.
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 17.12.2018
Subjects:	Encoder-decoder model Multi-scale attention CNN Saliency detection Encoder-decoder model Multi-scale attention CNN Saliency detection
ISSN:	0925-2312, 1872-8286
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!