Hyperspectral Image Classification Based on a Shuffled Group Convolutional Neural Network with Transfer Learning
Open Access
- 1 June 2020
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 12 (11), 1780
- https://doi.org/10.3390/rs12111780
Abstract
Convolutional neural networks (CNNs) have been widely applied in hyperspectral imagery (HSI) classification. However, their classification performance might be limited by the scarcity of labeled data to be used for training and validation. In this paper, we propose a novel lightweight shuffled group convolutional neural network (abbreviated as SG-CNN) to achieve efficient training with a limited training dataset in HSI classification. SG-CNN consists of SG conv units that employ conventional and atrous convolution in different groups, followed by channel shuffle operation and shortcut connection. In this way, SG-CNNs have less trainable parameters, whilst they can still be accurately and efficiently trained with fewer labeled samples. Transfer learning between different HSI datasets is also applied on the SG-CNN to further improve the classification accuracy. To evaluate the effectiveness of SG-CNNs for HSI classification, experiments have been conducted on three public HSI datasets pretrained on HSIs from different sensors. SG-CNNs with different levels of complexity were tested, and their classification results were compared with fine-tuned ShuffleNet2, ResNeXt, and their original counterparts. The experimental results demonstrate that SG-CNNs can achieve competitive classification performance when the amount of labeled data for training is poor, as well as efficiently providing satisfying classification results.Keywords
Funding Information
- National Natural Science Foundation of China (41901304, 41722108)
This publication has 41 references indexed in Scilit:
- Spectral–Spatial Classification of Hyperspectral Image Based on Deep Auto-EncoderIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016
- Application of hyperspectral remote sensing to cyanobacterial blooms in inland watersRemote Sensing of Environment, 2015
- Hyperspectral classificationviadeep networks and superpixel segmentationInternational Journal of Remote Sensing, 2015
- Generation of Spectral–Temporal Response Surfaces by Combining Multispectral Satellite and Hyperspectral UAV Imagery for Precision Agriculture ApplicationsIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015
- Deep Convolutional Neural Networks for Hyperspectral Image ClassificationJournal of Sensors, 2015
- Deep Learning-Based Classification of Hyperspectral DataIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014
- Airborne hyperspectral remote sensing to assess spatial distribution of water quality characteristics in large rivers: The Mississippi River and its tributaries in MinnesotaRemote Sensing of Environment, 2013
- Application of hyperspectral remote sensing for environment monitoring in mining areasEnvironmental Earth Sciences, 2011
- The Performance of Maximum Likelihood, Spectral Angle Mapper, Neural Network and Decision Tree Classifiers in Hyperspectral Image AnalysisJournal of Computer Science, 2007
- Preprocessing eo-1 hyperion hyperspectral data to support the application of agricultural indexesIEEE Transactions on Geoscience and Remote Sensing, 2003