Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385209904> ?p ?o ?g. }
- W4385209904 endingPage "8451" @default.
- W4385209904 startingPage "8451" @default.
- W4385209904 abstract "Recently, deep learning tools have made significant progress in hyperspectral image (HSI) classification. Most of existing methods implement a patch-based classification manner which may cause training test information leakage or waste labeled information for non-central pixels of image patches. Therefore, it is challenging to achieve remarkable classification performance via the traditional convolutional neural networks (CNN) in the absence of label information. Moreover, due to the limitation of convolutional kernel sizes and convolution operations, the spectral information of HSI cannot be fully utilized with a traditional CNN framework. In this paper, we implement pixel-based classification by a special data division strategy and propose a novel spatial–spectral dimensional transformation (SSDT) to obtain spectral features containing more spectral information. Then, we construct a fully convolutional network (FCN) with two branches based on 3D-FCN and 2D-FCN to achieve broader spatial and spectral information interaction. Finally, the fused features are utilized to realize accurate pixel-based classification. We verify our proposed method on three classic publicly available datasets; the overall classification accuracy and average accuracy reach 82.27%/87.85%, 83.81%/81.55%, and 85.97%/83.89%. Compared with the latest proposed method SS3FCN in the no-information-leakage scenario, the overall classification accuracy of our proposed method is improved by 1.72%, 4.95% and 0.2%, and the average accuracy is improved by 0.95%, 3.92% and 2.67% on the three databases, respectively. Experimental results demonstrate the effectiveness of the proposed SSDT and the proposed CNN framework." @default.
- W4385209904 created "2023-07-25" @default.
- W4385209904 creator A5011120737 @default.
- W4385209904 creator A5033987622 @default.
- W4385209904 creator A5053839400 @default.
- W4385209904 creator A5067303374 @default.
- W4385209904 creator A5067869362 @default.
- W4385209904 date "2023-07-21" @default.
- W4385209904 modified "2023-10-02" @default.
- W4385209904 title "Learning Spatial–Spectral-Dimensional-Transformation-Based Features for Hyperspectral Image Classification" @default.
- W4385209904 cites W1903029394 @default.
- W4385209904 cites W1993022127 @default.
- W4385209904 cites W1998030312 @default.
- W4385209904 cites W2069231830 @default.
- W4385209904 cites W2088657558 @default.
- W4385209904 cites W2090424610 @default.
- W4385209904 cites W2131725398 @default.
- W4385209904 cites W2150990614 @default.
- W4385209904 cites W2155359044 @default.
- W4385209904 cites W2294445779 @default.
- W4385209904 cites W2412588858 @default.
- W4385209904 cites W2507855991 @default.
- W4385209904 cites W2548791488 @default.
- W4385209904 cites W2572303978 @default.
- W4385209904 cites W2611655888 @default.
- W4385209904 cites W2618530766 @default.
- W4385209904 cites W2752782242 @default.
- W4385209904 cites W2789643644 @default.
- W4385209904 cites W2792059834 @default.
- W4385209904 cites W2900246877 @default.
- W4385209904 cites W2937675449 @default.
- W4385209904 cites W2950325582 @default.
- W4385209904 cites W2955446216 @default.
- W4385209904 cites W2962770389 @default.
- W4385209904 cites W2963351448 @default.
- W4385209904 cites W2978620371 @default.
- W4385209904 cites W2992919850 @default.
- W4385209904 cites W3003552243 @default.
- W4385209904 cites W3005414792 @default.
- W4385209904 cites W3010420609 @default.
- W4385209904 cites W3186879605 @default.
- W4385209904 doi "https://doi.org/10.3390/app13148451" @default.
- W4385209904 hasPublicationYear "2023" @default.
- W4385209904 type Work @default.
- W4385209904 citedByCount "0" @default.
- W4385209904 crossrefType "journal-article" @default.
- W4385209904 hasAuthorship W4385209904A5011120737 @default.
- W4385209904 hasAuthorship W4385209904A5033987622 @default.
- W4385209904 hasAuthorship W4385209904A5053839400 @default.
- W4385209904 hasAuthorship W4385209904A5067303374 @default.
- W4385209904 hasAuthorship W4385209904A5067869362 @default.
- W4385209904 hasBestOaLocation W43852099041 @default.
- W4385209904 hasConcept C104317684 @default.
- W4385209904 hasConcept C114614502 @default.
- W4385209904 hasConcept C115961682 @default.
- W4385209904 hasConcept C153180895 @default.
- W4385209904 hasConcept C154945302 @default.
- W4385209904 hasConcept C159078339 @default.
- W4385209904 hasConcept C159620131 @default.
- W4385209904 hasConcept C160633673 @default.
- W4385209904 hasConcept C185592680 @default.
- W4385209904 hasConcept C204241405 @default.
- W4385209904 hasConcept C205649164 @default.
- W4385209904 hasConcept C33923547 @default.
- W4385209904 hasConcept C41008148 @default.
- W4385209904 hasConcept C55493867 @default.
- W4385209904 hasConcept C62649853 @default.
- W4385209904 hasConcept C74193536 @default.
- W4385209904 hasConcept C75294576 @default.
- W4385209904 hasConcept C81363708 @default.
- W4385209904 hasConceptScore W4385209904C104317684 @default.
- W4385209904 hasConceptScore W4385209904C114614502 @default.
- W4385209904 hasConceptScore W4385209904C115961682 @default.
- W4385209904 hasConceptScore W4385209904C153180895 @default.
- W4385209904 hasConceptScore W4385209904C154945302 @default.
- W4385209904 hasConceptScore W4385209904C159078339 @default.
- W4385209904 hasConceptScore W4385209904C159620131 @default.
- W4385209904 hasConceptScore W4385209904C160633673 @default.
- W4385209904 hasConceptScore W4385209904C185592680 @default.
- W4385209904 hasConceptScore W4385209904C204241405 @default.
- W4385209904 hasConceptScore W4385209904C205649164 @default.
- W4385209904 hasConceptScore W4385209904C33923547 @default.
- W4385209904 hasConceptScore W4385209904C41008148 @default.
- W4385209904 hasConceptScore W4385209904C55493867 @default.
- W4385209904 hasConceptScore W4385209904C62649853 @default.
- W4385209904 hasConceptScore W4385209904C74193536 @default.
- W4385209904 hasConceptScore W4385209904C75294576 @default.
- W4385209904 hasConceptScore W4385209904C81363708 @default.
- W4385209904 hasIssue "14" @default.
- W4385209904 hasLocation W43852099041 @default.
- W4385209904 hasOpenAccess W4385209904 @default.
- W4385209904 hasPrimaryLocation W43852099041 @default.
- W4385209904 hasRelatedWork W2004746362 @default.
- W4385209904 hasRelatedWork W2546645752 @default.
- W4385209904 hasRelatedWork W2765939201 @default.
- W4385209904 hasRelatedWork W2781623059 @default.
- W4385209904 hasRelatedWork W2807839383 @default.
- W4385209904 hasRelatedWork W2972973180 @default.