Next Article in Journal
Small PN-Code Lidar for Asteroid and Comet Missions—Receiver Processing and Performance Simulations
Previous Article in Journal
Space-Time Evolutions of Land Subsidence in the Choushui River Alluvial Fan (Taiwan) from Multiple-Sensor Observations
Previous Article in Special Issue
Intra-Annual Variabilities of Rubus caesius L. Discrimination on Hyperspectral and LiDAR Data
Communication

Regularized CNN Feature Hierarchy for Hyperspectral Image Classification

1
Department of Computer Science, Chiniot-Faisalabad Campus, National University of Computer and Emerging Sciences, Islamabad, Chiniot 35400, Pakistan
2
Dipartimento di Matematica e Informatica-MIFT, University of Messina, 98121 Messina, Italy
3
Institute of Software Development and Engineering, Innopolis University, 420500 Innopolis, Russia
*
Author to whom correspondence should be addressed.
Academic Editor: Bogdan Zagajewski
Remote Sens. 2021, 13(12), 2275; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13122275
Received: 28 April 2021 / Revised: 2 June 2021 / Accepted: 7 June 2021 / Published: 10 June 2021
(This article belongs to the Special Issue Hyperspectral Remote Sensing: Current Situation and New Challenges)
Convolutional Neural Networks (CNN) have been rigorously studied for Hyperspectral Image Classification (HSIC) and are known to be effective in exploiting joint spatial-spectral information with the expense of lower generalization performance and learning speed due to the hard labels and non-uniform distribution over labels. Therefore, this paper proposed an idea to enhance the generalization performance of CNN for HSIC using soft labels that are a weighted average of the hard labels and uniform distribution over ground labels. The proposed method helps to prevent CNN from becoming over-confident. We empirically show that, in improving generalization performance, regularization also improves model calibration, which significantly improves beam-search. Several publicly available Hyperspectral datasets are used to validate the experimental evaluation, which reveals improved performance as compared to the state-of-the-art models with overall 99.29%, 99.97%, and 100.0% accuracy for Indiana Pines, Pavia University, and Salinas dataset, respectively. View Full-Text
Keywords: beam-search; regularization; hybrid convolutional neural network (CNN); hyperspectral images classification (HSIC) beam-search; regularization; hybrid convolutional neural network (CNN); hyperspectral images classification (HSIC)
Show Figures

Figure 1

MDPI and ACS Style

Ahmad, M.; Mazzara, M.; Distefano, S. Regularized CNN Feature Hierarchy for Hyperspectral Image Classification. Remote Sens. 2021, 13, 2275. https://0-doi-org.brum.beds.ac.uk/10.3390/rs13122275

AMA Style

Ahmad M, Mazzara M, Distefano S. Regularized CNN Feature Hierarchy for Hyperspectral Image Classification. Remote Sensing. 2021; 13(12):2275. https://0-doi-org.brum.beds.ac.uk/10.3390/rs13122275

Chicago/Turabian Style

Ahmad, Muhammad, Manuel Mazzara, and Salvatore Distefano. 2021. "Regularized CNN Feature Hierarchy for Hyperspectral Image Classification" Remote Sensing 13, no. 12: 2275. https://0-doi-org.brum.beds.ac.uk/10.3390/rs13122275

Find Other Styles
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