SGA-Net: Self-Constructing Graph Attention Neural Network for Semantic Segmentation of Remote Sensing Images

Semantic segmentation of remote sensing images is always a critical and challenging task. Graph neural networks, which can capture global contextual representations, can exploit long-range pixel dependency, thereby improving semantic segmentation performance. In this paper, a novel self-constructing...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Wenjie Zi, Wei Xiong, Hao Chen, Jun Li, Ning Jing
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	self-constructing graph semantic segmentation remote sensing Science Q
Acceso en línea:	https://doaj.org/article/02f707f793094988899e14798dc514e2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:02f707f793094988899e14798dc514e2
record_format	dspace
spelling	oai:doaj.org-article:02f707f793094988899e14798dc514e22021-11-11T18:49:49ZSGA-Net: Self-Constructing Graph Attention Neural Network for Semantic Segmentation of Remote Sensing Images10.3390/rs132142012072-4292https://doaj.org/article/02f707f793094988899e14798dc514e22021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4201https://doaj.org/toc/2072-4292Semantic segmentation of remote sensing images is always a critical and challenging task. Graph neural networks, which can capture global contextual representations, can exploit long-range pixel dependency, thereby improving semantic segmentation performance. In this paper, a novel self-constructing graph attention neural network is proposed for such a purpose. Firstly, ResNet50 was employed as backbone of a feature extraction network to acquire feature maps of remote sensing images. Secondly, pixel-wise dependency graphs were constructed from the feature maps of images, and a graph attention network is designed to extract the correlations of pixels of the remote sensing images. Thirdly, the channel linear attention mechanism obtained the channel dependency of images, further improving the prediction of semantic segmentation. Lastly, we conducted comprehensive experiments and found that the proposed model consistently outperformed state-of-the-art methods on two widely used remote sensing image datasets.Wenjie ZiWei XiongHao ChenJun LiNing JingMDPI AGarticleself-constructing graphsemantic segmentationremote sensingScienceQENRemote Sensing, Vol 13, Iss 4201, p 4201 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	self-constructing graph semantic segmentation remote sensing Science Q
spellingShingle	self-constructing graph semantic segmentation remote sensing Science Q Wenjie Zi Wei Xiong Hao Chen Jun Li Ning Jing SGA-Net: Self-Constructing Graph Attention Neural Network for Semantic Segmentation of Remote Sensing Images
description	Semantic segmentation of remote sensing images is always a critical and challenging task. Graph neural networks, which can capture global contextual representations, can exploit long-range pixel dependency, thereby improving semantic segmentation performance. In this paper, a novel self-constructing graph attention neural network is proposed for such a purpose. Firstly, ResNet50 was employed as backbone of a feature extraction network to acquire feature maps of remote sensing images. Secondly, pixel-wise dependency graphs were constructed from the feature maps of images, and a graph attention network is designed to extract the correlations of pixels of the remote sensing images. Thirdly, the channel linear attention mechanism obtained the channel dependency of images, further improving the prediction of semantic segmentation. Lastly, we conducted comprehensive experiments and found that the proposed model consistently outperformed state-of-the-art methods on two widely used remote sensing image datasets.
format	article
author	Wenjie Zi Wei Xiong Hao Chen Jun Li Ning Jing
author_facet	Wenjie Zi Wei Xiong Hao Chen Jun Li Ning Jing
author_sort	Wenjie Zi
title	SGA-Net: Self-Constructing Graph Attention Neural Network for Semantic Segmentation of Remote Sensing Images
title_short	SGA-Net: Self-Constructing Graph Attention Neural Network for Semantic Segmentation of Remote Sensing Images
title_full	SGA-Net: Self-Constructing Graph Attention Neural Network for Semantic Segmentation of Remote Sensing Images
title_fullStr	SGA-Net: Self-Constructing Graph Attention Neural Network for Semantic Segmentation of Remote Sensing Images
title_full_unstemmed	SGA-Net: Self-Constructing Graph Attention Neural Network for Semantic Segmentation of Remote Sensing Images
title_sort	sga-net: self-constructing graph attention neural network for semantic segmentation of remote sensing images
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/02f707f793094988899e14798dc514e2
work_keys_str_mv	AT wenjiezi sganetselfconstructinggraphattentionneuralnetworkforsemanticsegmentationofremotesensingimages AT weixiong sganetselfconstructinggraphattentionneuralnetworkforsemanticsegmentationofremotesensingimages AT haochen sganetselfconstructinggraphattentionneuralnetworkforsemanticsegmentationofremotesensingimages AT junli sganetselfconstructinggraphattentionneuralnetworkforsemanticsegmentationofremotesensingimages AT ningjing sganetselfconstructinggraphattentionneuralnetworkforsemanticsegmentationofremotesensingimages
_version_	1718431683721560064

SGA-Net: Self-Constructing Graph Attention Neural Network for Semantic Segmentation of Remote Sensing Images

Ejemplares similares