TY - GEN
T1 - Learning Region Response Ranking Features for Remote Sensing Image Scene Classification
AU - Yang, Junyu
AU - Cheng, Gong
AU - Yao, Xiwen
AU - Han, Junwei
AU - Guo, Lei
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/7
Y1 - 2019/7
N2 - Recently, deep learning especially convolutional neural networks (CNNs) has huge great success for remote sensing image scene classification. However, global CNN features still lack geometric invariance for addressing the problem of large intra-class variations and so are not optimal for scene classification. In this paper, we introduce a new feature representation for scene classification, named region response ranking (3R) feature representations by using off-the-shelf CNN models. Specifically, by considering each cube pixel of a certain convolutional feature map as one image region, we jointly train a class-specific support vector machine (SVM) base classifier and a decision function for each scene class. The base classifier is used to generate 3R feature by reordering the SVM responses of all image regions in descending order and the decision function is used for classification with 3R feature representations. Comprehensive evaluations on the publicly available NWPU-RESISC45 data set and comparisons with state-of-the-art methods demonstrate that the proposed 3R feature is effective for remote sensing image scene classification.1
AB - Recently, deep learning especially convolutional neural networks (CNNs) has huge great success for remote sensing image scene classification. However, global CNN features still lack geometric invariance for addressing the problem of large intra-class variations and so are not optimal for scene classification. In this paper, we introduce a new feature representation for scene classification, named region response ranking (3R) feature representations by using off-the-shelf CNN models. Specifically, by considering each cube pixel of a certain convolutional feature map as one image region, we jointly train a class-specific support vector machine (SVM) base classifier and a decision function for each scene class. The base classifier is used to generate 3R feature by reordering the SVM responses of all image regions in descending order and the decision function is used for classification with 3R feature representations. Comprehensive evaluations on the publicly available NWPU-RESISC45 data set and comparisons with state-of-the-art methods demonstrate that the proposed 3R feature is effective for remote sensing image scene classification.1
KW - convolutional neural network (CNN)
KW - region response ranking (3R) feature
KW - Remote sensing image
KW - scene classification
UR - http://www.scopus.com/inward/record.url?scp=85077714560&partnerID=8YFLogxK
U2 - 10.1109/IGARSS.2019.8897886
DO - 10.1109/IGARSS.2019.8897886
M3 - 会议稿件
AN - SCOPUS:85077714560
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 529
EP - 532
BT - 2019 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019
Y2 - 28 July 2019 through 2 August 2019
ER -