FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226043457> ?p ?o ?g. }

• W4226043457 endingPage "18" @default.
• W4226043457 startingPage "1" @default.
• W4226043457 abstract "The existing hyperspectral image (HSI) classification encounters the obstacle of improving the classification accuracy with limited labeled samples. In this context, as a typical implementation of meta-learning, few-shot learning (FSL) makes the model learn by episodic training on source HSI, which has achieved significant improvements in small sample classification of target HSI. However, the existing FSL methods lack explicit consideration and exploration of the association between pixels, especially the intraclass association and interclass association between pixels in the support set and query set. To mitigate these issues, an FSL method based on edge-labeling graph neural network (FSL-EGNN) is proposed for small sample classification of HSI, which is the first attempt to explicitly quantify the associations between pixels by exploiting EGNN in HSI few-shot classification (FSC). Specifically, based on graph construction of HSI, episodic training is performed on the existing source HSI. During training, EGNN is used to predict the edge labels on the graph, thereby explicitly modeling the intraclass similarity and interclass dissimilarity between pixels of HSI. After the trained model is fine-tuned, it can realize FSC on the unseen target HSI. Experiments conducted on three benchmark HSI datasets demonstrate that the proposed FSL-EGNN outperforms the existing state-of-the-art methods with limited labeled samples." @default.
• W4226043457 created "2022-05-05" @default.
• W4226043457 creator A5001486765 @default.
• W4226043457 creator A5027117106 @default.
• W4226043457 creator A5034523235 @default.
• W4226043457 creator A5039991862 @default.
• W4226043457 creator A5047270197 @default.
• W4226043457 date "2022-01-01" @default.
• W4226043457 modified "2023-10-05" @default.
• W4226043457 title "FSL-EGNN: Edge-Labeling Graph Neural Network for Hyperspectral Image Few-Shot Classification" @default.
• W4226043457 cites W1950365613 @default.
• W4226043457 cites W2029316659 @default.
• W4226043457 cites W2090424610 @default.
• W4226043457 cites W2136251662 @default.
• W4226043457 cites W2152057649 @default.
• W4226043457 cites W2154240401 @default.
• W4226043457 cites W2464755555 @default.
• W4226043457 cites W2500751094 @default.
• W4226043457 cites W2521284359 @default.
• W4226043457 cites W2620547787 @default.
• W4226043457 cites W2757208835 @default.
• W4226043457 cites W2764276316 @default.
• W4226043457 cites W2767651786 @default.
• W4226043457 cites W2767805377 @default.
• W4226043457 cites W2768537477 @default.
• W4226043457 cites W2782517596 @default.
• W4226043457 cites W2791006446 @default.
• W4226043457 cites W2822065499 @default.
• W4226043457 cites W2888119354 @default.
• W4226043457 cites W2892621946 @default.
• W4226043457 cites W2898204262 @default.
• W4226043457 cites W2898381489 @default.
• W4226043457 cites W2920277426 @default.
• W4226043457 cites W2940678725 @default.
• W4226043457 cites W2944413439 @default.
• W4226043457 cites W2944512710 @default.
• W4226043457 cites W2945989246 @default.
• W4226043457 cites W2948157022 @default.
• W4226043457 cites W2966751049 @default.
• W4226043457 cites W2979923697 @default.
• W4226043457 cites W2981151698 @default.
• W4226043457 cites W2983217715 @default.
• W4226043457 cites W2991494819 @default.
• W4226043457 cites W2991616716 @default.
• W4226043457 cites W3011645114 @default.
• W4226043457 cites W3012405452 @default.
• W4226043457 cites W3014253313 @default.
• W4226043457 cites W3015347340 @default.
• W4226043457 cites W3034100957 @default.
• W4226043457 cites W3037458146 @default.
• W4226043457 cites W3041694656 @default.
• W4226043457 cites W3080919303 @default.
• W4226043457 cites W3089684975 @default.
• W4226043457 cites W3099850646 @default.
• W4226043457 cites W3100011500 @default.
• W4226043457 cites W3103753223 @default.
• W4226043457 cites W3107591966 @default.
• W4226043457 cites W3119839606 @default.
• W4226043457 cites W3125860323 @default.
• W4226043457 cites W3132867842 @default.
• W4226043457 cites W3133704440 @default.
• W4226043457 cites W3137622667 @default.
• W4226043457 cites W3157130577 @default.
• W4226043457 cites W3163755067 @default.
• W4226043457 cites W3166273387 @default.
• W4226043457 cites W3184654054 @default.
• W4226043457 cites W3192648206 @default.
• W4226043457 cites W3195184408 @default.
• W4226043457 cites W3198812651 @default.
• W4226043457 cites W3202921355 @default.
• W4226043457 cites W3205614732 @default.
• W4226043457 cites W3206770096 @default.
• W4226043457 cites W4205573763 @default.
• W4226043457 cites W4210268724 @default.
• W4226043457 cites W4240485910 @default.
• W4226043457 doi "https://doi.org/10.1109/tgrs.2022.3165025" @default.
• W4226043457 hasPublicationYear "2022" @default.
• W4226043457 type Work @default.
• W4226043457 citedByCount "8" @default.
• W4226043457 countsByYear W42260434572022 @default.
• W4226043457 countsByYear W42260434572023 @default.
• W4226043457 crossrefType "journal-article" @default.
• W4226043457 hasAuthorship W4226043457A5001486765 @default.
• W4226043457 hasAuthorship W4226043457A5027117106 @default.
• W4226043457 hasAuthorship W4226043457A5034523235 @default.
• W4226043457 hasAuthorship W4226043457A5039991862 @default.
• W4226043457 hasAuthorship W4226043457A5047270197 @default.
• W4226043457 hasConcept C115961682 @default.
• W4226043457 hasConcept C132525143 @default.
• W4226043457 hasConcept C151730666 @default.
• W4226043457 hasConcept C153180895 @default.
• W4226043457 hasConcept C154945302 @default.
• W4226043457 hasConcept C159078339 @default.
• W4226043457 hasConcept C160633673 @default.
• W4226043457 hasConcept C2779343474 @default.
• W4226043457 hasConcept C31972630 @default.
• W4226043457 hasConcept C41008148 @default.
• W4226043457 hasConcept C50644808 @default.

• next