FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202805802> ?p ?o ?g. }

• W3202805802 endingPage "10241" @default.
• W3202805802 startingPage "10226" @default.
• W3202805802 abstract "Abundant spectral features are the precious wealth of hyperspectral images (HSI). Nevertheless, well-designed spectral feature is still a challenge that affects the performance of the classifier, especially with insufficient number of training samples. To make up the poor discriminability of spectral feature, double-branch methods are proposed by fusing parallel spectral and spatial branches. However, this structure does nothing to improve the quality of spectral feature, which is regarded as the most valuable information for hyperspectral image information. In this paper, we propose a siamese spectral attention network with channel consistency (SSACC) to focus on obtaining discriminative spectral features, thus improving the generalization ability of the classifier. Two kinds of HSI cubes with different patch sizes are generated as the input of SSACC. The two cubes are divided into top and bottom branches and then be fed into the siamese network to obtain the refined spectral features. Then, self-attention is conducted to interacting with each channel for the spectral features enhancement. Meanwhile, two attention maps are obtained to display the spectral structures of each branch. A channel consistency regularization is performed on the two attention maps by enforcing the two branches to possess similar spectral patterns when identifying the same centric pixel. Extensive experiments conducted on the three HSI datasets verify the superiority of the obtained spectral feature. Furthermore, the proposed method applying convolution only on the spectral domain outperforms the state-of-the-art double-branch methods which integrate the spectral and spatial features simultaneously." @default.
• W3202805802 created "2021-10-11" @default.
• W3202805802 creator A5031199063 @default.
• W3202805802 creator A5046779897 @default.
• W3202805802 creator A5062275094 @default.
• W3202805802 creator A5072254497 @default.
• W3202805802 creator A5091211713 @default.
• W3202805802 date "2021-01-01" @default.
• W3202805802 modified "2023-09-23" @default.
• W3202805802 title "Siamese Spectral Attention With Channel Consistency for Hyperspectral Image Classification" @default.
• W3202805802 cites W1521436688 @default.
• W3202805802 cites W2029061115 @default.
• W3202805802 cites W2087263574 @default.
• W3202805802 cites W2097117768 @default.
• W3202805802 cites W2102605133 @default.
• W3202805802 cites W2106277226 @default.
• W3202805802 cites W2136251662 @default.
• W3202805802 cites W2162698522 @default.
• W3202805802 cites W248389711 @default.
• W3202805802 cites W2500751094 @default.
• W3202805802 cites W2548791488 @default.
• W3202805802 cites W2602024454 @default.
• W3202805802 cites W2745461083 @default.
• W3202805802 cites W2754356769 @default.
• W3202805802 cites W2764276316 @default.
• W3202805802 cites W2767805377 @default.
• W3202805802 cites W2777427437 @default.
• W3202805802 cites W2780799698 @default.
• W3202805802 cites W2789643644 @default.
• W3202805802 cites W2800371750 @default.
• W3202805802 cites W2888715336 @default.
• W3202805802 cites W2899747753 @default.
• W3202805802 cites W2908955282 @default.
• W3202805802 cites W2944653015 @default.
• W3202805802 cites W2946028165 @default.
• W3202805802 cites W2948157022 @default.
• W3202805802 cites W2950266692 @default.
• W3202805802 cites W2963091558 @default.
• W3202805802 cites W2963446712 @default.
• W3202805802 cites W2966751049 @default.
• W3202805802 cites W2977002487 @default.
• W3202805802 cites W2982220924 @default.
• W3202805802 cites W2983062821 @default.
• W3202805802 cites W2989871747 @default.
• W3202805802 cites W2994050370 @default.
• W3202805802 cites W2999446243 @default.
• W3202805802 cites W3000289760 @default.
• W3202805802 cites W3007536931 @default.
• W3202805802 cites W3031696400 @default.
• W3202805802 cites W3032908737 @default.
• W3202805802 cites W3034339621 @default.
• W3202805802 cites W3034552520 @default.
• W3202805802 cites W3040102868 @default.
• W3202805802 cites W3043181422 @default.
• W3202805802 cites W3046007115 @default.
• W3202805802 cites W3047443805 @default.
• W3202805802 cites W3100011500 @default.
• W3202805802 cites W3100958491 @default.
• W3202805802 cites W3103753223 @default.
• W3202805802 cites W3114720220 @default.
• W3202805802 cites W3119997721 @default.
• W3202805802 cites W3123061203 @default.
• W3202805802 cites W3125860323 @default.
• W3202805802 cites W3128571866 @default.
• W3202805802 cites W4240485910 @default.
• W3202805802 doi "https://doi.org/10.1109/jstars.2021.3115129" @default.
• W3202805802 hasPublicationYear "2021" @default.
• W3202805802 type Work @default.
• W3202805802 sameAs 3202805802 @default.
• W3202805802 citedByCount "3" @default.
• W3202805802 countsByYear W32028058022022 @default.
• W3202805802 countsByYear W32028058022023 @default.
• W3202805802 crossrefType "journal-article" @default.
• W3202805802 hasAuthorship W3202805802A5031199063 @default.
• W3202805802 hasAuthorship W3202805802A5046779897 @default.
• W3202805802 hasAuthorship W3202805802A5062275094 @default.
• W3202805802 hasAuthorship W3202805802A5072254497 @default.
• W3202805802 hasAuthorship W3202805802A5091211713 @default.
• W3202805802 hasBestOaLocation W32028058021 @default.
• W3202805802 hasConcept C114700698 @default.
• W3202805802 hasConcept C127162648 @default.
• W3202805802 hasConcept C127313418 @default.
• W3202805802 hasConcept C138885662 @default.
• W3202805802 hasConcept C153180895 @default.
• W3202805802 hasConcept C154945302 @default.
• W3202805802 hasConcept C159078339 @default.
• W3202805802 hasConcept C160633673 @default.
• W3202805802 hasConcept C176641082 @default.
• W3202805802 hasConcept C2776401178 @default.
• W3202805802 hasConcept C31258907 @default.
• W3202805802 hasConcept C3232514 @default.
• W3202805802 hasConcept C33923547 @default.
• W3202805802 hasConcept C41008148 @default.
• W3202805802 hasConcept C41895202 @default.
• W3202805802 hasConcept C62649853 @default.
• W3202805802 hasConcept C95623464 @default.
• W3202805802 hasConcept C97931131 @default.
• W3202805802 hasConceptScore W3202805802C114700698 @default.

• next