Dual Interactive Graph Convolutional Networks for Hyperspectral Image Classification

Wan, S; Pan, S; Zhong, P; Chang, X; Yang, J; Gong, C

Dual Interactive Graph Convolutional Networks for Hyperspectral Image Classification

Wan, S Pan, S

Zhong, P Chang, X

Yang, J Gong, C

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE Transactions on Geoscience and Remote Sensing, 2022, 60
Issue Date:: 2022-01-01

Closed Access

	Filename	Description	Size
	Dual_Interactive_Graph_Convolutional_Networks_for_Hyperspectral_Image_Classification.pdf	Published version	4.46 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Wan, S
dc.contributor.author	Pan, S https://orcid.org/0000-0003-0794-527X
dc.contributor.author	Zhong, P
dc.contributor.author	Chang, X https://orcid.org/0000-0002-7778-8807
dc.contributor.author	Yang, J
dc.contributor.author	Gong, C
dc.date.accessioned	2023-03-23T00:50:00Z
dc.date.available	2023-03-23T00:50:00Z
dc.date.issued	2022-01-01
dc.identifier.citation	IEEE Transactions on Geoscience and Remote Sensing, 2022, 60
dc.identifier.issn	0196-2892
dc.identifier.issn	1558-0644
dc.identifier.uri	http://hdl.handle.net/10453/168120
dc.description.abstract	Recently, graph convolutional network (GCN) has progressed significantly and gained increasing attention in hyperspectral image (HSI) classification due to its impressive representation power. However, existing GCN-based methods do not give full consideration to the multiscale spatial information, since the convolution operations are governed by fixed neighborhood. As a result, their performances can be limited, particularly in the regions with diverse land cover appearances. In this article, we develop a new dual interactive GCN (DIGCN) which introduces the dual GCN branches to capture spatial information at different scales. More significantly, the dual interactive module is embedded across the GCN branches, so that the correlation of multiscale spatial information can be leveraged to refine the graph information. To be concrete, the edge information contained in one GCN branch can be refined by incorporating the feature representations from the other branch. Analogously, improved feature representations can be generated in one GCN branch by fusing the edge information from the other branch. As such, the refined graph information can help enhance the representation power of the model. Furthermore, to avoid the negative effects of the manually constructed graph, our proposed model adaptively learns a discriminative region-induced graph, which also accelerates the convolution operation. We comprehensively evaluate the proposed method on four commonly used HSI benchmark data sets, and the state-of-the-art results can be achieved when compared with several typical HSI classification methods.
dc.language	English
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation.ispartof	IEEE Transactions on Geoscience and Remote Sensing
dc.relation.isbasedon	10.1109/TGRS.2021.3075223
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0404 Geophysics, 0906 Electrical and Electronic Engineering, 0909 Geomatic Engineering
dc.subject.classification	Geological & Geomatics Engineering
dc.title	Dual Interactive Graph Convolutional Networks for Hyperspectral Image Classification
dc.type	Journal Article
utslib.citation.volume	60
utslib.for	0404 Geophysics
utslib.for	0906 Electrical and Electronic Engineering
utslib.for	0909 Geomatic Engineering
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
utslib.copyright.status	closed_access	*
dc.date.updated	2023-03-23T00:49:59Z
pubs.publication-status	Published
pubs.volume	60

Abstract:

Recently, graph convolutional network (GCN) has progressed significantly and gained increasing attention in hyperspectral image (HSI) classification due to its impressive representation power. However, existing GCN-based methods do not give full consideration to the multiscale spatial information, since the convolution operations are governed by fixed neighborhood. As a result, their performances can be limited, particularly in the regions with diverse land cover appearances. In this article, we develop a new dual interactive GCN (DIGCN) which introduces the dual GCN branches to capture spatial information at different scales. More significantly, the dual interactive module is embedded across the GCN branches, so that the correlation of multiscale spatial information can be leveraged to refine the graph information. To be concrete, the edge information contained in one GCN branch can be refined by incorporating the feature representations from the other branch. Analogously, improved feature representations can be generated in one GCN branch by fusing the edge information from the other branch. As such, the refined graph information can help enhance the representation power of the model. Furthermore, to avoid the negative effects of the manually constructed graph, our proposed model adaptively learns a discriminative region-induced graph, which also accelerates the convolution operation. We comprehensively evaluate the proposed method on four commonly used HSI benchmark data sets, and the state-of-the-art results can be achieved when compared with several typical HSI classification methods.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/168120