Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385859309> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4385859309 endingPage "5" @default.
- W4385859309 startingPage "1" @default.
- W4385859309 abstract "Both local and global context dependencies are essential for building extraction from remote sensing (RS) images. Convolutional Neural Network (CNN) can extract local spatial details well but lacks the ability to model long-range dependency. In recent years, Vision Transformer (ViT) have shown great potential in modeling global context dependency. However, it usually brings huge computational cost, and spatial details can not be fully retained in the process of feature extraction. To maximize the advantages of CNNs and ViTs, we propose DSAT-Net, which combine them in one model. In DSAT-Net, we design an efficient Dual Spatial Attention Transformer (DSAFormer) to solve the defects of standard ViT. It has a dual attention structure to complement each other. Specifically, the global attention path (GAP) conducts a large scale down sampling of the feature maps before the global self-attention computing, to reduce the computational cost. The local attention path (LAP) uses efficient stripe convolution to generate local attention, which can alleviate the loss of information caused by down-sampling operation in the GAP and supplement the spatial details. In addition, we design a feature refining module called Channel Mixing Feature Refine Module (CM-FRM) to fuse low-level and high-level features. Our model achieved competitive results on three public building extraction datasets. Code will be available at: https://github.com/stdcoutzrh/BuildingExtraction." @default.
- W4385859309 created "2023-08-17" @default.
- W4385859309 creator A5025931513 @default.
- W4385859309 creator A5058424158 @default.
- W4385859309 creator A5060120202 @default.
- W4385859309 creator A5076850388 @default.
- W4385859309 date "2023-01-01" @default.
- W4385859309 modified "2023-10-17" @default.
- W4385859309 title "DSAT-Net: Dual Spatial Attention Transformer for Building Extraction From Aerial Images" @default.
- W4385859309 cites W1903029394 @default.
- W4385859309 cites W2908320224 @default.
- W4385859309 cites W2996327453 @default.
- W4385859309 cites W3110440461 @default.
- W4385859309 cites W3131500599 @default.
- W4385859309 cites W3138516171 @default.
- W4385859309 cites W3161825146 @default.
- W4385859309 cites W3183174367 @default.
- W4385859309 cites W3217005392 @default.
- W4385859309 cites W4214893857 @default.
- W4385859309 cites W4226289601 @default.
- W4385859309 cites W4309325582 @default.
- W4385859309 cites W4312443924 @default.
- W4385859309 cites W4319157933 @default.
- W4385859309 doi "https://doi.org/10.1109/lgrs.2023.3304377" @default.
- W4385859309 hasPublicationYear "2023" @default.
- W4385859309 type Work @default.
- W4385859309 citedByCount "0" @default.
- W4385859309 crossrefType "journal-article" @default.
- W4385859309 hasAuthorship W4385859309A5025931513 @default.
- W4385859309 hasAuthorship W4385859309A5058424158 @default.
- W4385859309 hasAuthorship W4385859309A5060120202 @default.
- W4385859309 hasAuthorship W4385859309A5076850388 @default.
- W4385859309 hasConcept C121332964 @default.
- W4385859309 hasConcept C153180895 @default.
- W4385859309 hasConcept C154945302 @default.
- W4385859309 hasConcept C165801399 @default.
- W4385859309 hasConcept C41008148 @default.
- W4385859309 hasConcept C52622490 @default.
- W4385859309 hasConcept C62520636 @default.
- W4385859309 hasConcept C66322947 @default.
- W4385859309 hasConcept C81363708 @default.
- W4385859309 hasConceptScore W4385859309C121332964 @default.
- W4385859309 hasConceptScore W4385859309C153180895 @default.
- W4385859309 hasConceptScore W4385859309C154945302 @default.
- W4385859309 hasConceptScore W4385859309C165801399 @default.
- W4385859309 hasConceptScore W4385859309C41008148 @default.
- W4385859309 hasConceptScore W4385859309C52622490 @default.
- W4385859309 hasConceptScore W4385859309C62520636 @default.
- W4385859309 hasConceptScore W4385859309C66322947 @default.
- W4385859309 hasConceptScore W4385859309C81363708 @default.
- W4385859309 hasFunder F4320309612 @default.
- W4385859309 hasFunder F4320321001 @default.
- W4385859309 hasFunder F4320321885 @default.
- W4385859309 hasLocation W43858593091 @default.
- W4385859309 hasOpenAccess W4385859309 @default.
- W4385859309 hasPrimaryLocation W43858593091 @default.
- W4385859309 hasRelatedWork W2033213769 @default.
- W4385859309 hasRelatedWork W2033914206 @default.
- W4385859309 hasRelatedWork W2042327336 @default.
- W4385859309 hasRelatedWork W2056912418 @default.
- W4385859309 hasRelatedWork W2112208972 @default.
- W4385859309 hasRelatedWork W2123759770 @default.
- W4385859309 hasRelatedWork W2151520854 @default.
- W4385859309 hasRelatedWork W2373006798 @default.
- W4385859309 hasRelatedWork W2601157893 @default.
- W4385859309 hasRelatedWork W2811390910 @default.
- W4385859309 hasVolume "20" @default.
- W4385859309 isParatext "false" @default.
- W4385859309 isRetracted "false" @default.
- W4385859309 workType "article" @default.