FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226068448> ?p ?o ?g. }

• W4226068448 endingPage "3957" @default.
• W4226068448 startingPage "3948" @default.
• W4226068448 abstract "The nonlinear relation between the spectral information and the corresponding objects (complex physiognomies) makes pixel-wise classification challenging for conventional methods. To deal with nonlinearity issues in Hyperspectral Image Classification (HISC), Convolutional Neural Networks (CNN) are more suitable, indeed. However, fixed kernel sizes make traditional CNN too specific, neither flexible nor conducive to feature learning, thus impacting on the classification accuracy. The convolution of different kernel size networks may overcome this problem by capturing more discriminating and relevant information. In light of this, the proposed solution aims at combining the core idea of 3D and 2D Inception net with the Attention mechanism to boost the HSIC CNN performance in a hybrid scenario. The resulting textit{attention-fused hybrid network} (AfNet) is based on three attention-fused parallel hybrid sub-nets with different kernels in each block repeatedly using high-level features to enhance the final ground-truth maps. In short, AfNet is able to selectively filter out the discriminative features critical for classification. Several tests on HSI datasets provided competitive results for AfNet compared to state-of-the-art models. The proposed pipeline achieved, indeed, an overall accuracy of 97% for the Indian Pines, 100% for Botswana, 99% for Pavia University, Pavia Center, and Salinas datasets." @default.
• W4226068448 created "2022-05-05" @default.
• W4226068448 creator A5022103201 @default.
• W4226068448 creator A5044102676 @default.
• W4226068448 creator A5070522496 @default.
• W4226068448 creator A5075175655 @default.
• W4226068448 creator A5079443694 @default.
• W4226068448 creator A5087427076 @default.
• W4226068448 date "2022-01-01" @default.
• W4226068448 modified "2023-09-26" @default.
• W4226068448 title "Hybrid Dense Network With Attention Mechanism for Hyperspectral Image Classification" @default.
• W4226068448 cites W1584663654 @default.
• W4226068448 cites W1958291604 @default.
• W4226068448 cites W2100495367 @default.
• W4226068448 cites W2113513024 @default.
• W4226068448 cites W2162698522 @default.
• W4226068448 cites W2164315346 @default.
• W4226068448 cites W2167685974 @default.
• W4226068448 cites W2194775991 @default.
• W4226068448 cites W2572303978 @default.
• W4226068448 cites W2752782242 @default.
• W4226068448 cites W2764276316 @default.
• W4226068448 cites W2767805377 @default.
• W4226068448 cites W2768038330 @default.
• W4226068448 cites W2902746003 @default.
• W4226068448 cites W2908955282 @default.
• W4226068448 cites W2914331134 @default.
• W4226068448 cites W2948157022 @default.
• W4226068448 cites W2963091558 @default.
• W4226068448 cites W2969881582 @default.
• W4226068448 cites W2977355106 @default.
• W4226068448 cites W2982220924 @default.
• W4226068448 cites W2983062821 @default.
• W4226068448 cites W2988517117 @default.
• W4226068448 cites W3002489160 @default.
• W4226068448 cites W3034552520 @default.
• W4226068448 cites W3040988483 @default.
• W4226068448 cites W3047443805 @default.
• W4226068448 cites W3048631361 @default.
• W4226068448 cites W3082072668 @default.
• W4226068448 cites W3088984088 @default.
• W4226068448 cites W3090223510 @default.
• W4226068448 cites W3094904775 @default.
• W4226068448 cites W3100714546 @default.
• W4226068448 cites W3101012758 @default.
• W4226068448 cites W3122774149 @default.
• W4226068448 cites W3135445258 @default.
• W4226068448 cites W3140885850 @default.
• W4226068448 cites W3154512708 @default.
• W4226068448 cites W3157380831 @default.
• W4226068448 cites W3164229442 @default.
• W4226068448 cites W3165362898 @default.
• W4226068448 cites W3165729427 @default.
• W4226068448 cites W3167109952 @default.
• W4226068448 cites W3168367808 @default.
• W4226068448 cites W3214821343 @default.
• W4226068448 cites W4210692941 @default.
• W4226068448 doi "https://doi.org/10.1109/jstars.2022.3171586" @default.
• W4226068448 hasPublicationYear "2022" @default.
• W4226068448 type Work @default.
• W4226068448 citedByCount "6" @default.
• W4226068448 countsByYear W42260684482022 @default.
• W4226068448 countsByYear W42260684482023 @default.
• W4226068448 crossrefType "journal-article" @default.
• W4226068448 hasAuthorship W4226068448A5022103201 @default.
• W4226068448 hasAuthorship W4226068448A5044102676 @default.
• W4226068448 hasAuthorship W4226068448A5070522496 @default.
• W4226068448 hasAuthorship W4226068448A5075175655 @default.
• W4226068448 hasAuthorship W4226068448A5079443694 @default.
• W4226068448 hasAuthorship W4226068448A5087427076 @default.
• W4226068448 hasBestOaLocation W42260684481 @default.
• W4226068448 hasConcept C114614502 @default.
• W4226068448 hasConcept C12267149 @default.
• W4226068448 hasConcept C138885662 @default.
• W4226068448 hasConcept C153180895 @default.
• W4226068448 hasConcept C154945302 @default.
• W4226068448 hasConcept C159078339 @default.
• W4226068448 hasConcept C160633673 @default.
• W4226068448 hasConcept C199360897 @default.
• W4226068448 hasConcept C2524010 @default.
• W4226068448 hasConcept C2776401178 @default.
• W4226068448 hasConcept C2777210771 @default.
• W4226068448 hasConcept C33923547 @default.
• W4226068448 hasConcept C41008148 @default.
• W4226068448 hasConcept C41895202 @default.
• W4226068448 hasConcept C43521106 @default.
• W4226068448 hasConcept C45347329 @default.
• W4226068448 hasConcept C50644808 @default.
• W4226068448 hasConcept C52622490 @default.
• W4226068448 hasConcept C74193536 @default.
• W4226068448 hasConcept C81363708 @default.
• W4226068448 hasConcept C97931131 @default.
• W4226068448 hasConceptScore W4226068448C114614502 @default.
• W4226068448 hasConceptScore W4226068448C12267149 @default.
• W4226068448 hasConceptScore W4226068448C138885662 @default.
• W4226068448 hasConceptScore W4226068448C153180895 @default.
• W4226068448 hasConceptScore W4226068448C154945302 @default.
• W4226068448 hasConceptScore W4226068448C159078339 @default.

• next