FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313558738> ?p ?o ?g. }

• W4313558738 endingPage "316" @default.
• W4313558738 startingPage "316" @default.
• W4313558738 abstract "Hyperspectral Image (HSI) classification methods that use Deep Learning (DL) have proven to be effective in recent years. In particular, Convolutional Neural Networks (CNNs) have demonstrated extremely powerful performance in such tasks. However, the lack of training samples is one of the main contributors to low classification performance. Traditional CNN-based techniques under-utilize the inter-band correlations of HSI because they primarily use 2D-CNNs for feature extraction. Contrariwise, 3D-CNNs extract both spectral and spatial information using the same operation. While this overcomes the limitation of 2D-CNNs, it may lead to insufficient extraction of features. In order to overcome this issue, we propose an HSI classification approach named Tri-CNN which is based on a multi-scale 3D-CNN and three-branch feature fusion. We first extract HSI features using 3D-CNN at various scales. The three different features are then flattened and concatenated. To obtain the classification results, the fused features then traverse a number of fully connected layers and eventually a softmax layer. Experimental results are conducted on three datasets, Pavia University (PU), Salinas scene (SA) and GulfPort (GP) datasets, respectively. Classification results indicate that our proposed methodology shows remarkable performance in terms of the Overall Accuracy (OA), Average Accuracy (AA), and Kappa metrics when compared against existing methods." @default.
• W4313558738 created "2023-01-06" @default.
• W4313558738 creator A5013850016 @default.
• W4313558738 creator A5021086706 @default.
• W4313558738 creator A5026377367 @default.
• W4313558738 creator A5029163925 @default.
• W4313558738 creator A5043785449 @default.
• W4313558738 creator A5060659198 @default.
• W4313558738 creator A5082466450 @default.
• W4313558738 date "2023-01-05" @default.
• W4313558738 modified "2023-10-15" @default.
• W4313558738 title "Tri-CNN: A Three Branch Model for Hyperspectral Image Classification" @default.
• W4313558738 cites W1977949977 @default.
• W4313558738 cites W1992961908 @default.
• W4313558738 cites W2050497921 @default.
• W4313558738 cites W2121338139 @default.
• W4313558738 cites W2136251662 @default.
• W4313558738 cites W2499682827 @default.
• W4313558738 cites W2500751094 @default.
• W4313558738 cites W2765366036 @default.
• W4313558738 cites W2766146978 @default.
• W4313558738 cites W2772452219 @default.
• W4313558738 cites W2782517596 @default.
• W4313558738 cites W2791006446 @default.
• W4313558738 cites W2890670700 @default.
• W4313558738 cites W2914331134 @default.
• W4313558738 cites W2936517889 @default.
• W4313558738 cites W2941387379 @default.
• W4313558738 cites W2961290969 @default.
• W4313558738 cites W2975144662 @default.
• W4313558738 cites W2983277052 @default.
• W4313558738 cites W2992919850 @default.
• W4313558738 cites W3003717368 @default.
• W4313558738 cites W3008774450 @default.
• W4313558738 cites W3009887759 @default.
• W4313558738 cites W3013953267 @default.
• W4313558738 cites W3037490781 @default.
• W4313558738 cites W3037874508 @default.
• W4313558738 cites W3049736620 @default.
• W4313558738 cites W3075397214 @default.
• W4313558738 cites W3097590716 @default.
• W4313558738 cites W3100011500 @default.
• W4313558738 cites W3101640299 @default.
• W4313558738 cites W3105357426 @default.
• W4313558738 cites W3116511560 @default.
• W4313558738 cites W3132524115 @default.
• W4313558738 cites W3133411644 @default.
• W4313558738 cites W3139745482 @default.
• W4313558738 cites W3156646782 @default.
• W4313558738 cites W3184654054 @default.
• W4313558738 cites W4220805125 @default.
• W4313558738 cites W4221136930 @default.
• W4313558738 cites W4224981559 @default.
• W4313558738 cites W4229066610 @default.
• W4313558738 cites W4237591687 @default.
• W4313558738 cites W4240485910 @default.
• W4313558738 cites W4285803842 @default.
• W4313558738 cites W4291366441 @default.
• W4313558738 cites W4293099986 @default.
• W4313558738 doi "https://doi.org/10.3390/rs15020316" @default.
• W4313558738 hasPublicationYear "2023" @default.
• W4313558738 type Work @default.
• W4313558738 citedByCount "10" @default.
• W4313558738 countsByYear W43135587382023 @default.
• W4313558738 crossrefType "journal-article" @default.
• W4313558738 hasAuthorship W4313558738A5013850016 @default.
• W4313558738 hasAuthorship W4313558738A5021086706 @default.
• W4313558738 hasAuthorship W4313558738A5026377367 @default.
• W4313558738 hasAuthorship W4313558738A5029163925 @default.
• W4313558738 hasAuthorship W4313558738A5043785449 @default.
• W4313558738 hasAuthorship W4313558738A5060659198 @default.
• W4313558738 hasAuthorship W4313558738A5082466450 @default.
• W4313558738 hasBestOaLocation W43135587381 @default.
• W4313558738 hasConcept C138885662 @default.
• W4313558738 hasConcept C153180895 @default.
• W4313558738 hasConcept C154945302 @default.
• W4313558738 hasConcept C159078339 @default.
• W4313558738 hasConcept C176809094 @default.
• W4313558738 hasConcept C188441871 @default.
• W4313558738 hasConcept C205649164 @default.
• W4313558738 hasConcept C2776401178 @default.
• W4313558738 hasConcept C41008148 @default.
• W4313558738 hasConcept C41895202 @default.
• W4313558738 hasConcept C52622490 @default.
• W4313558738 hasConcept C58640448 @default.
• W4313558738 hasConcept C81363708 @default.
• W4313558738 hasConceptScore W4313558738C138885662 @default.
• W4313558738 hasConceptScore W4313558738C153180895 @default.
• W4313558738 hasConceptScore W4313558738C154945302 @default.
• W4313558738 hasConceptScore W4313558738C159078339 @default.
• W4313558738 hasConceptScore W4313558738C176809094 @default.
• W4313558738 hasConceptScore W4313558738C188441871 @default.
• W4313558738 hasConceptScore W4313558738C205649164 @default.
• W4313558738 hasConceptScore W4313558738C2776401178 @default.
• W4313558738 hasConceptScore W4313558738C41008148 @default.
• W4313558738 hasConceptScore W4313558738C41895202 @default.
• W4313558738 hasConceptScore W4313558738C52622490 @default.
• W4313558738 hasConceptScore W4313558738C58640448 @default.

• next