Paper Info
Title
High Precision Detection of Salient Objects Based on Deep Convolutional Networks with Proper Combinations of Shallow and Deep Connections.
Abstract
In this paper, a high precision detection method of salient objects is presented based on deep convolutional networks with proper combinations of shallow and deep connections. In order to achieve better performance in the extraction of deep semantic features of salient objects, based on a symmetric encoder and decoder architecture, an upgrade of backbone networks is carried out with a transferable model on the ImageNet pre-trained ResNet50. Moreover, by introducing shallow and deep connections on multiple side outputs, feature maps generated from various layers of the deep neural network (DNN) model are well fused so as to describe salient objects from local and global aspects comprehensively. Afterwards, based on a holistically nested edge detector (HED) architecture, multiple fused side outputs with various sizes of receptive fields are integrated to form detection results of salient objects accordingly. A series of experiments and assessments on extensive benchmark datasets demonstrate the dominant performance of our DNN model for the detection of salient objects in accuracy, which has outperformed those of other published works.
Year
DOI
Venue
2019
10.3390/sym11010005
SYMMETRY-BASEL
Keywords
Field
DocType
detection of salient objects,deep learning,deep neural networks,semantic segmentation,shallow and deep connections
Architecture,Pattern recognition,Mathematical analysis,Salient objects,Decoder architecture,Edge detector,Upgrade,Encoder,Artificial intelligence,Deep learning,Artificial neural network,Mathematics
Journal
Volume
Issue
Citations 
11
1
2
PageRank 
References 
Authors
0.38
22
2
Name
Order
Citations
PageRank
Lin Guo1188.58
Shiyin Qin221320.72