Deep Convolutional Highway Unit Network for SAR Target Classification With Limited Labeled Training Data

The deep convolutional neural network (CNN) has been widely used for target classification, because it can learn highly useful representations from data. However, it is difficult to apply a CNN for synthetic aperture radar (SAR) target classification directly, for it often requires a large volume of...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE geoscience and remote sensing letters Ročník 14; číslo 7; s. 1091 - 1095
Hlavní autori: Lin, Zhao, Ji, Kefeng, Kang, Miao, Leng, Xiangguang, Zou, Huanxin
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Piscataway IEEE 01.07.2017
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Accuracy
Architecture
Classification
Convolutional neural network (CNN)
Data
deep learning
Feature extraction
feature representation
highway network
Model accuracy
Neural networks
Radar
Representations
Road transportation
SAR (radar)
Stacking
Synthetic aperture radar
syntheticaperture radar (SAR)
Target acquisition
Target recognition
Training
Training data
Transforms
Transportation networks
ISSN:1545-598X, 1558-0571
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The deep convolutional neural network (CNN) has been widely used for target classification, because it can learn highly useful representations from data. However, it is difficult to apply a CNN for synthetic aperture radar (SAR) target classification directly, for it often requires a large volume of labeled training data, which is impractical for SAR applications. The highway network is a newly proposed architecture based on CNN that can be trained with smaller data sets. This letter proposes a novel architecture called the convolutional highway unit to train deeper networks with limited SAR data. The unit architecture is formed by modified convolutional highway layers, a maxpool layer, and a dropout layer. Then, the networks can be flexibly formed by stacking the unit architecture to extract deep feature representations for classification. Experimental results on the moving and stationary target acquisition and recognition data set indicate that the branched ensemble model based on the unit architecture can achieve 99% classification accuracy with all training data. When the training data are reduced to 30%, the classification accuracy of the ensemble model can still reach 94.97%.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1545-598X
1558-0571
DOI:10.1109/LGRS.2017.2698213