Synergistic 2D/3D Convolutional Neural Network for hyperspectral image classification

Accurate hyperspectral image classification has been an important yet challenging task for years. With the recent success of deep learning in various tasks, 2-dimensional (2D)/3-dimensional (3D) convolutional neural networks (CNNs) have been exploited to capture spectral or spatial information in hy...

Full description

Saved in:
Bibliographic Details
Main Authors: Yang, Xiaofei, Zhang, Xiaofeng, Ye, Yunming, Lau, Raymond Y. K., Lu, Shijian, Li, Xutao, Huang, Xiaohui
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2021
Subjects:
Online Access:https://hdl.handle.net/10356/146021
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-146021
record_format dspace
spelling sg-ntu-dr.10356-1460212021-01-21T06:05:49Z Synergistic 2D/3D Convolutional Neural Network for hyperspectral image classification Yang, Xiaofei Zhang, Xiaofeng Ye, Yunming Lau, Raymond Y. K. Lu, Shijian Li, Xutao Huang, Xiaohui School of Computer Science and Engineering Engineering::Computer science and engineering Convolutional Neural Network 3D CNN Accurate hyperspectral image classification has been an important yet challenging task for years. With the recent success of deep learning in various tasks, 2-dimensional (2D)/3-dimensional (3D) convolutional neural networks (CNNs) have been exploited to capture spectral or spatial information in hyperspectral images. On the other hand, few approaches make use of both spectral and spatial information simultaneously, which is critical to accurate hyperspectral image classification. This paper presents a novel Synergistic Convolutional Neural Network (SyCNN) for accurate hyperspectral image classification. The SyCNN consists of a hybrid module that combines 2D and 3D CNNs in feature learning and a data interaction module that fuses spectral and spatial hyperspectral information. Additionally, it introduces a 3D attention mechanism before the fully-connected layer which helps filter out interfering features and information effectively. Extensive experiments over three public benchmarking datasets show that our proposed SyCNNs clearly outperform state-of-the-art techniques that use 2D/3D CNNs. Published version 2021-01-21T06:05:49Z 2021-01-21T06:05:49Z 2020 Journal Article Yang, X., Zhang, X., Ye, Y., Lau, R. Y. K., Lu, S., Li, X., & Huang, X. (2020). Synergistic 2D/3D Convolutional Neural Network for hyperspectral image classification. Remote Sensing, 12(12), 2033-. doi:10.3390/rs12122033 2072-4292 0000-0002-5751-4550 https://hdl.handle.net/10356/146021 10.3390/rs12122033 2-s2.0-85086986483 12 12 en Remote Sensing © 2020 The Authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Convolutional Neural Network
3D CNN
spellingShingle Engineering::Computer science and engineering
Convolutional Neural Network
3D CNN
Yang, Xiaofei
Zhang, Xiaofeng
Ye, Yunming
Lau, Raymond Y. K.
Lu, Shijian
Li, Xutao
Huang, Xiaohui
Synergistic 2D/3D Convolutional Neural Network for hyperspectral image classification
description Accurate hyperspectral image classification has been an important yet challenging task for years. With the recent success of deep learning in various tasks, 2-dimensional (2D)/3-dimensional (3D) convolutional neural networks (CNNs) have been exploited to capture spectral or spatial information in hyperspectral images. On the other hand, few approaches make use of both spectral and spatial information simultaneously, which is critical to accurate hyperspectral image classification. This paper presents a novel Synergistic Convolutional Neural Network (SyCNN) for accurate hyperspectral image classification. The SyCNN consists of a hybrid module that combines 2D and 3D CNNs in feature learning and a data interaction module that fuses spectral and spatial hyperspectral information. Additionally, it introduces a 3D attention mechanism before the fully-connected layer which helps filter out interfering features and information effectively. Extensive experiments over three public benchmarking datasets show that our proposed SyCNNs clearly outperform state-of-the-art techniques that use 2D/3D CNNs.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Yang, Xiaofei
Zhang, Xiaofeng
Ye, Yunming
Lau, Raymond Y. K.
Lu, Shijian
Li, Xutao
Huang, Xiaohui
format Article
author Yang, Xiaofei
Zhang, Xiaofeng
Ye, Yunming
Lau, Raymond Y. K.
Lu, Shijian
Li, Xutao
Huang, Xiaohui
author_sort Yang, Xiaofei
title Synergistic 2D/3D Convolutional Neural Network for hyperspectral image classification
title_short Synergistic 2D/3D Convolutional Neural Network for hyperspectral image classification
title_full Synergistic 2D/3D Convolutional Neural Network for hyperspectral image classification
title_fullStr Synergistic 2D/3D Convolutional Neural Network for hyperspectral image classification
title_full_unstemmed Synergistic 2D/3D Convolutional Neural Network for hyperspectral image classification
title_sort synergistic 2d/3d convolutional neural network for hyperspectral image classification
publishDate 2021
url https://hdl.handle.net/10356/146021
_version_ 1690658351787016192