Wide Sliding Window and Subsampling Network for Hyperspectral Image Classification
Recently, deep learning methods, for example, convolutional neural networks (CNNs), have achieved high performance in hyperspectral image (HSI) classification. The limited training samples of HSI images make it hard to use deep learning methods with many layers and a large number of convolutional ke...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-03-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/13/7/1290 |
id |
doaj-f2c86763c2bf4c7c89db8b67411b0601 |
---|---|
record_format |
Article |
spelling |
doaj-f2c86763c2bf4c7c89db8b67411b06012021-03-28T23:02:01ZengMDPI AGRemote Sensing2072-42922021-03-01131290129010.3390/rs13071290Wide Sliding Window and Subsampling Network for Hyperspectral Image ClassificationJiangbo Xi0Okan K. Ersoy1Jianwu Fang2Ming Cong3Tianjun Wu4Chaoying Zhao5Zhenhong Li6College of Geological Engineering and Geomatics, Chang’an University, Xi’an 710054, ChinaSchool of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USACollege of Transportation Engineering, Chang’an University, Xi’an 710064, ChinaCollege of Geological Engineering and Geomatics, Chang’an University, Xi’an 710054, ChinaDepartment of Mathematics and Information Science, College of Science, Chang’an University, Xi’an 710064, ChinaCollege of Geological Engineering and Geomatics, Chang’an University, Xi’an 710054, ChinaCollege of Geological Engineering and Geomatics, Chang’an University, Xi’an 710054, ChinaRecently, deep learning methods, for example, convolutional neural networks (CNNs), have achieved high performance in hyperspectral image (HSI) classification. The limited training samples of HSI images make it hard to use deep learning methods with many layers and a large number of convolutional kernels as in large scale imagery tasks, and CNN-based methods usually need long training time. In this paper, we present a wide sliding window and subsampling network (WSWS Net) for HSI classification. It is based on layers of transform kernels with sliding windows and subsampling (WSWS). It can be extended in the wide direction to learn both spatial and spectral features more efficiently. The learned features are subsampled to reduce computational loads and to reduce memorization. Thus, layers of WSWS can learn higher level spatial and spectral features efficiently, and the proposed network can be trained easily by only computing linear weights with least squares. The experimental results show that the WSWS Net achieves excellent performance with different hyperspectral remotes sensing datasets compared with other shallow and deep learning methods. The effects of ratio of training samples, the sizes of image patches, and the visualization of features in WSWS layers are presented.https://www.mdpi.com/2072-4292/13/7/1290hyperspectral image classification (HSI)convolutional neural network (CNN)wide sliding window and subsampling (WSWS) |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jiangbo Xi Okan K. Ersoy Jianwu Fang Ming Cong Tianjun Wu Chaoying Zhao Zhenhong Li |
spellingShingle |
Jiangbo Xi Okan K. Ersoy Jianwu Fang Ming Cong Tianjun Wu Chaoying Zhao Zhenhong Li Wide Sliding Window and Subsampling Network for Hyperspectral Image Classification Remote Sensing hyperspectral image classification (HSI) convolutional neural network (CNN) wide sliding window and subsampling (WSWS) |
author_facet |
Jiangbo Xi Okan K. Ersoy Jianwu Fang Ming Cong Tianjun Wu Chaoying Zhao Zhenhong Li |
author_sort |
Jiangbo Xi |
title |
Wide Sliding Window and Subsampling Network for Hyperspectral Image Classification |
title_short |
Wide Sliding Window and Subsampling Network for Hyperspectral Image Classification |
title_full |
Wide Sliding Window and Subsampling Network for Hyperspectral Image Classification |
title_fullStr |
Wide Sliding Window and Subsampling Network for Hyperspectral Image Classification |
title_full_unstemmed |
Wide Sliding Window and Subsampling Network for Hyperspectral Image Classification |
title_sort |
wide sliding window and subsampling network for hyperspectral image classification |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2021-03-01 |
description |
Recently, deep learning methods, for example, convolutional neural networks (CNNs), have achieved high performance in hyperspectral image (HSI) classification. The limited training samples of HSI images make it hard to use deep learning methods with many layers and a large number of convolutional kernels as in large scale imagery tasks, and CNN-based methods usually need long training time. In this paper, we present a wide sliding window and subsampling network (WSWS Net) for HSI classification. It is based on layers of transform kernels with sliding windows and subsampling (WSWS). It can be extended in the wide direction to learn both spatial and spectral features more efficiently. The learned features are subsampled to reduce computational loads and to reduce memorization. Thus, layers of WSWS can learn higher level spatial and spectral features efficiently, and the proposed network can be trained easily by only computing linear weights with least squares. The experimental results show that the WSWS Net achieves excellent performance with different hyperspectral remotes sensing datasets compared with other shallow and deep learning methods. The effects of ratio of training samples, the sizes of image patches, and the visualization of features in WSWS layers are presented. |
topic |
hyperspectral image classification (HSI) convolutional neural network (CNN) wide sliding window and subsampling (WSWS) |
url |
https://www.mdpi.com/2072-4292/13/7/1290 |
work_keys_str_mv |
AT jiangboxi wideslidingwindowandsubsamplingnetworkforhyperspectralimageclassification AT okankersoy wideslidingwindowandsubsamplingnetworkforhyperspectralimageclassification AT jianwufang wideslidingwindowandsubsamplingnetworkforhyperspectralimageclassification AT mingcong wideslidingwindowandsubsamplingnetworkforhyperspectralimageclassification AT tianjunwu wideslidingwindowandsubsamplingnetworkforhyperspectralimageclassification AT chaoyingzhao wideslidingwindowandsubsamplingnetworkforhyperspectralimageclassification AT zhenhongli wideslidingwindowandsubsamplingnetworkforhyperspectralimageclassification |
_version_ |
1724199454644371456 |