Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306964490> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W4306964490 endingPage "5251" @default.
- W4306964490 startingPage "5251" @default.
- W4306964490 abstract "Hyperspectral sensors provide an opportunity to capture the intensity of high spatial/spectral information and enable applications for high-level earth observation missions, such as accurate land cover mapping and target/object detection. Currently, convolutional neural networks (CNNs) are good at coping with hyperspectral image processing tasks because of the strong spatial and spectral feature extraction ability brought by hierarchical structures, but the convolution operation in CNNs is limited to local feature extraction in both dimensions. In the meanwhile, the introduction of the Transformer structure has provided an opportunity to capture long-distance dependencies between tokens from a global perspective; however, Transformer-based methods have a restricted ability to extract local information because they have no inductive bias, as CNNs do. To make full use of these two methods’ advantages in hyperspectral image processing, a dual-flow architecture named Hyper-LGNet to couple local and global features is firstly proposed by integrating CNN and Transformer branches to deal with HSI spatial-spectral information. In particular, a spatial-spectral feature fusion module (SSFFM) is designed to maximally integrate spectral and spatial information. Three mainstream hyperspectral datasets (Indian Pines, Pavia University and Houston 2013) are utilized to evaluate the proposed method’s performance. Comparative results show that the proposed Hyper-LGNet achieves state-of-the-art performance in comparison with the other nine approaches concerning overall accuracy (OA), average accuracy (AA) and kappa index. Consequently, it is anticipated that, by coupling CNN and Transformer structures, this study can provide novel insights into hyperspectral image analysis." @default.
- W4306964490 created "2022-10-21" @default.
- W4306964490 creator A5038565459 @default.
- W4306964490 creator A5051252943 @default.
- W4306964490 creator A5055420643 @default.
- W4306964490 creator A5070021733 @default.
- W4306964490 creator A5074215202 @default.
- W4306964490 creator A5076427021 @default.
- W4306964490 date "2022-10-20" @default.
- W4306964490 modified "2023-10-18" @default.
- W4306964490 title "Hyper-LGNet: Coupling Local and Global Features for Hyperspectral Image Classification" @default.
- W4306964490 cites W1521436688 @default.
- W4306964490 cites W2307094448 @default.
- W4306964490 cites W2500751094 @default.
- W4306964490 cites W2548791488 @default.
- W4306964490 cites W2581139755 @default.
- W4306964490 cites W2603834682 @default.
- W4306964490 cites W2757242159 @default.
- W4306964490 cites W2764276316 @default.
- W4306964490 cites W2770641139 @default.
- W4306964490 cites W2793272303 @default.
- W4306964490 cites W2793941577 @default.
- W4306964490 cites W2799390666 @default.
- W4306964490 cites W2804458818 @default.
- W4306964490 cites W2804532080 @default.
- W4306964490 cites W2889400155 @default.
- W4306964490 cites W2944512710 @default.
- W4306964490 cites W2946747211 @default.
- W4306964490 cites W2950266692 @default.
- W4306964490 cites W2952234521 @default.
- W4306964490 cites W2962770389 @default.
- W4306964490 cites W2971432438 @default.
- W4306964490 cites W2991494819 @default.
- W4306964490 cites W2991616716 @default.
- W4306964490 cites W3047317383 @default.
- W4306964490 cites W3047443805 @default.
- W4306964490 cites W3091245084 @default.
- W4306964490 cites W3100011500 @default.
- W4306964490 cites W3127327694 @default.
- W4306964490 cites W3128776197 @default.
- W4306964490 cites W3138725786 @default.
- W4306964490 cites W3167109952 @default.
- W4306964490 cites W3174710842 @default.
- W4306964490 cites W3192524834 @default.
- W4306964490 cites W3209540366 @default.
- W4306964490 cites W3214821343 @default.
- W4306964490 cites W4210785162 @default.
- W4306964490 cites W4213019189 @default.
- W4306964490 doi "https://doi.org/10.3390/rs14205251" @default.
- W4306964490 hasPublicationYear "2022" @default.
- W4306964490 type Work @default.
- W4306964490 citedByCount "3" @default.
- W4306964490 countsByYear W43069644902023 @default.
- W4306964490 crossrefType "journal-article" @default.
- W4306964490 hasAuthorship W4306964490A5038565459 @default.
- W4306964490 hasAuthorship W4306964490A5051252943 @default.
- W4306964490 hasAuthorship W4306964490A5055420643 @default.
- W4306964490 hasAuthorship W4306964490A5070021733 @default.
- W4306964490 hasAuthorship W4306964490A5074215202 @default.
- W4306964490 hasAuthorship W4306964490A5076427021 @default.
- W4306964490 hasBestOaLocation W43069644901 @default.
- W4306964490 hasConcept C153180895 @default.
- W4306964490 hasConcept C154945302 @default.
- W4306964490 hasConcept C159078339 @default.
- W4306964490 hasConcept C159620131 @default.
- W4306964490 hasConcept C205649164 @default.
- W4306964490 hasConcept C41008148 @default.
- W4306964490 hasConcept C52622490 @default.
- W4306964490 hasConcept C62649853 @default.
- W4306964490 hasConcept C81363708 @default.
- W4306964490 hasConceptScore W4306964490C153180895 @default.
- W4306964490 hasConceptScore W4306964490C154945302 @default.
- W4306964490 hasConceptScore W4306964490C159078339 @default.
- W4306964490 hasConceptScore W4306964490C159620131 @default.
- W4306964490 hasConceptScore W4306964490C205649164 @default.
- W4306964490 hasConceptScore W4306964490C41008148 @default.
- W4306964490 hasConceptScore W4306964490C52622490 @default.
- W4306964490 hasConceptScore W4306964490C62649853 @default.
- W4306964490 hasConceptScore W4306964490C81363708 @default.
- W4306964490 hasIssue "20" @default.
- W4306964490 hasLocation W43069644901 @default.
- W4306964490 hasOpenAccess W4306964490 @default.
- W4306964490 hasPrimaryLocation W43069644901 @default.
- W4306964490 hasRelatedWork W2033213769 @default.
- W4306964490 hasRelatedWork W2056912418 @default.
- W4306964490 hasRelatedWork W2112208972 @default.
- W4306964490 hasRelatedWork W2123759770 @default.
- W4306964490 hasRelatedWork W2151520854 @default.
- W4306964490 hasRelatedWork W2373006798 @default.
- W4306964490 hasRelatedWork W2601157893 @default.
- W4306964490 hasRelatedWork W2768048376 @default.
- W4306964490 hasRelatedWork W2811390910 @default.
- W4306964490 hasRelatedWork W4312376745 @default.
- W4306964490 hasVolume "14" @default.
- W4306964490 isParatext "false" @default.
- W4306964490 isRetracted "false" @default.
- W4306964490 workType "article" @default.