TY - GEN
T1 - Fusing different levels of deep features by deep stacked neural network for hyperspectral images
AU - Mei, Shaohui
AU - Chen, Yanfu
AU - Ji, Jingyu
AU - Hou, Junhui
AU - Du, Qian
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/12/1
Y1 - 2017/12/1
N2 - Deep learning techniques have been demonstrated to be a powerful tool to learn features of images automatically. In this paper, a novel deep learning structure, i.e., deep stacked neural network (DSNN), is constructed to extract different levels of deep features of hyperspectral images. Specifically, convolutional neural network (CNN) is used as basic units in the proposed DSNN for feature extraction of hyperspectral images. Then, different levels of deep features are concatenated to form a novel fused feature for classification with a typical classifier, e.g., SVM. Experimental results on two benchmark hyperspectral datasets show that the fusion of features extracted in DSNN can produce higher classification accuracy than state-of-the-art deep learning based methods, indicating its effectiveness in feature learning.
AB - Deep learning techniques have been demonstrated to be a powerful tool to learn features of images automatically. In this paper, a novel deep learning structure, i.e., deep stacked neural network (DSNN), is constructed to extract different levels of deep features of hyperspectral images. Specifically, convolutional neural network (CNN) is used as basic units in the proposed DSNN for feature extraction of hyperspectral images. Then, different levels of deep features are concatenated to form a novel fused feature for classification with a typical classifier, e.g., SVM. Experimental results on two benchmark hyperspectral datasets show that the fusion of features extracted in DSNN can produce higher classification accuracy than state-of-the-art deep learning based methods, indicating its effectiveness in feature learning.
KW - convolutional neural network
KW - deep learning
KW - deep stacked neural network
KW - feature fusion
KW - feature learning
UR - http://www.scopus.com/inward/record.url?scp=85041847081&partnerID=8YFLogxK
U2 - 10.1109/IGARSS.2017.8127063
DO - 10.1109/IGARSS.2017.8127063
M3 - 会议稿件
AN - SCOPUS:85041847081
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 759
EP - 762
BT - 2017 IEEE International Geoscience and Remote Sensing Symposium
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 37th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2017
Y2 - 23 July 2017 through 28 July 2017
ER -