Rights statement: ©2021 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Accepted author manuscript, 848 KB, PDF document
Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License
Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - First and Second-order Information Fusion Networks for Remote Sensing Scene Classification
AU - Li, Erzhu
AU - Samat, Alim
AU - Zhang, Ce
AU - Du, Peijun
AU - Liu, Wei
N1 - ©2021 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
PY - 2022/1/1
Y1 - 2022/1/1
N2 - Deep convolutional networks have been the most competitive method in remote sensing scene classification. Due to the diversity and complexity of scene content, remote sensing scene classification still remains a challenging task. Recently, the second-order pooling method has attracted more interest because it can learn higher-order information and enhance the non-linear modeling ability of the networks. However, how to effectively learn second-order features and establish the discriminative feature representation of holistic images is still an open question. In this Letter, we propose a first and second-order information fusion networks (FSoI-Net) that can learn the first-order and second-order features at the same time, and construct the final feature representation by fusing the two types of features. Specifically, a self-attention-based second-order pooling (SaSoP) method based on covariance matrix is proposed to extract second-order features, and a fusion loss function is developed to jointly train the model and construct the final feature representation for the classification decision. The proposed networks have been thoroughly evaluated on three real remote sensing scene datasets and achieved better performance than the counterparts.
AB - Deep convolutional networks have been the most competitive method in remote sensing scene classification. Due to the diversity and complexity of scene content, remote sensing scene classification still remains a challenging task. Recently, the second-order pooling method has attracted more interest because it can learn higher-order information and enhance the non-linear modeling ability of the networks. However, how to effectively learn second-order features and establish the discriminative feature representation of holistic images is still an open question. In this Letter, we propose a first and second-order information fusion networks (FSoI-Net) that can learn the first-order and second-order features at the same time, and construct the final feature representation by fusing the two types of features. Specifically, a self-attention-based second-order pooling (SaSoP) method based on covariance matrix is proposed to extract second-order features, and a fusion loss function is developed to jointly train the model and construct the final feature representation for the classification decision. The proposed networks have been thoroughly evaluated on three real remote sensing scene datasets and achieved better performance than the counterparts.
KW - Deep learning
KW - second-order pooling
KW - self-attention mechanism
KW - information fusion
KW - scene classification
U2 - 10.1109/LGRS.2021.3090045
DO - 10.1109/LGRS.2021.3090045
M3 - Journal article
VL - 19
JO - IEEE Geoscience and Remote Sensing Letters
JF - IEEE Geoscience and Remote Sensing Letters
SN - 1545-598X
M1 - 8009406
ER -