Next Article in Journal
Individual Tree Crown Delineation from Airborne Laser Scanning for Diseased Larch Forest Stands
Previous Article in Journal
Improved Class-Specific Codebook with Two-Step Classification for Scene-Level Classification of High Resolution Remote Sensing Images
Open AccessArticle

Transferring Pre-Trained Deep CNNs for Remote Scene Classification with General Features Learned from Linear PCA Network

1
Air and Missile Defense College, Air Force Engineering University, Xi’an 710051, China
2
Aeronautics and Astronautics Engineering College, Air Force Engineering University, Xi’an 710038, China
*
Author to whom correspondence should be addressed.
Academic Editors: Gonzalo Pajares Martinsanz and Prasad S. Thenkabail
Remote Sens. 2017, 9(3), 225; https://doi.org/10.3390/rs9030225
Received: 19 December 2016 / Accepted: 25 February 2017 / Published: 2 March 2017
Deep convolutional neural networks (CNNs) have been widely used to obtain high-level representation in various computer vision tasks. However, in the field of remote sensing, there are not sufficient images to train a useful deep CNN. Instead, we tend to transfer successful pre-trained deep CNNs to remote sensing tasks. In the transferring process, generalization power of features in pre-trained deep CNNs plays the key role. In this paper, we propose two promising architectures to extract general features from pre-trained deep CNNs for remote scene classification. These two architectures suggest two directions for improvement. First, before the pre-trained deep CNNs, we design a linear PCA network (LPCANet) to synthesize spatial information of remote sensing images in each spectral channel. This design shortens the spatial “distance” of target and source datasets for pre-trained deep CNNs. Second, we introduce quaternion algebra to LPCANet, which further shortens the spectral “distance” between remote sensing images and images used to pre-train deep CNNs. With five well-known pre-trained deep CNNs, experimental results on three independent remote sensing datasets demonstrate that our proposed framework obtains state-of-the-art results without fine-tuning and feature fusing. This paper also provides baseline for transferring fresh pretrained deep CNNs to other remote sensing tasks. View Full-Text
Keywords: convolutional neural network; remote scene classification; general feature; principle component analysis; deep learning convolutional neural network; remote scene classification; general feature; principle component analysis; deep learning
Show Figures

Graphical abstract

MDPI and ACS Style

Wang, J.; Luo, C.; Huang, H.; Zhao, H.; Wang, S. Transferring Pre-Trained Deep CNNs for Remote Scene Classification with General Features Learned from Linear PCA Network. Remote Sens. 2017, 9, 225.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop