Next Article in Journal
Impact of Sea Breeze Dynamics on Atmospheric Pollutants and Their Toxicity in Industrial and Urban Coastal Environments
Previous Article in Journal
Identifying Sheep Activity from Tri-Axial Acceleration Signals Using a Moving Window Classification Model
Previous Article in Special Issue
Mapping the Topographic Features of Mining-Related Valley Fills Using Mask R-CNN Deep Learning and Digital Elevation Data
Open AccessArticle

Deep Quadruplet Network for Hyperspectral Image Classification with a Small Number of Samples

by Chengye Zhang 1,2,3, Jun Yue 2,* and Qiming Qin 2
1
State Key Laboratory of Coal Resources and Safe Mining, China University of Mining & Technology (Beijing), Beijing 100083, China
2
Institute of Remote Sensing and Geographic Information System, School of Earth and Space Sciences, Peking University, Beijing 100871, China
3
College of Geoscience and Surveying Engineering, China University of Mining & Technology (Beijing), Beijing 100083, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(4), 647; https://doi.org/10.3390/rs12040647 (registering DOI)
Received: 17 January 2020 / Revised: 12 February 2020 / Accepted: 13 February 2020 / Published: 15 February 2020
This study proposes a deep quadruplet network (DQN) for hyperspectral image classification given the limitation of having a small number of samples. A quadruplet network is designed, which makes use of a new quadruplet loss function in order to learn a feature space where the distances between samples from the same class are shortened, while those from a different class are enlarged. A deep 3-D convolutional neural network (CNN) with characteristics of both dense convolution and dilated convolution is then employed and embedded in the quadruplet network to extract spatial-spectral features. Finally, the nearest neighbor (NN) classifier is used to accomplish the classification in the learned feature space. The results show that the proposed network can learn a feature space and is able to undertake hyperspectral image classification using only a limited number of samples. The main highlights of the study include: (1) The proposed approach was found to have high overall accuracy and can be classified as state-of-the-art; (2) Results of the ablation study suggest that all the modules of the proposed approach are effective in improving accuracy and that the proposed quadruplet loss contributes the most; (3) Time-analysis shows the proposed methodology has a similar level of time consumption as compared with existing methods. View Full-Text
Keywords: deep learning; hyperspectral image classification; few-shot learning; quadruplet loss; dense network; dilated convolutional network deep learning; hyperspectral image classification; few-shot learning; quadruplet loss; dense network; dilated convolutional network
Show Figures

Graphical abstract

MDPI and ACS Style

Zhang, C.; Yue, J.; Qin, Q. Deep Quadruplet Network for Hyperspectral Image Classification with a Small Number of Samples. Remote Sens. 2020, 12, 647.

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
Back to TopTop