Matches in SemOpenAlex for { <https://semopenalex.org/work/W4324360044> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4324360044 endingPage "103256" @default.
- W4324360044 startingPage "103256" @default.
- W4324360044 abstract "Accurate detection of land cover changes on the basis of very-high-resolution remote sensing is essential for many practical applications, like urban management, ecological health monitoring, and disaster loss assessment. Modern change detection (CD) methods are mostly based on convolutional neural network (CNN). Despite the good performance, CNN-based methods are restricted by the receptive field size and lack the ability of exploring the long-range dependencies in space–time. To address this issue, we propose a transformer-based CD model, which we called “multi-level difference aggregation transformer (MDAFormer)”. The proposed MDAFormer first employs a pair of deep-aware transformer encoders to learn the deep feature representations. Also, a feature difference aggregation module can be utilized to bridge the semantic gaps by aggregating multi-level feature differences, which generates distinguished feature maps. In the decoder, these feature differences are upsampled to the same resolution and further aggregated together, followed by a progressive residual recovery module to refine these features. Finally, a weighted multi-scale constraint loss function is employed to mitigate the impact of class imbalance. The experimental results on three datasets demonstrate the effectiveness of MDAFormer in CD tasks." @default.
- W4324360044 created "2023-03-16" @default.
- W4324360044 creator A5030672015 @default.
- W4324360044 creator A5043449790 @default.
- W4324360044 creator A5064639473 @default.
- W4324360044 date "2023-04-01" @default.
- W4324360044 modified "2023-10-14" @default.
- W4324360044 title "MDAFormer: Multi-level difference aggregation transformer for change detection of VHR optical imagery" @default.
- W4324360044 cites W1964669384 @default.
- W4324360044 cites W2006383776 @default.
- W4324360044 cites W2132222679 @default.
- W4324360044 cites W2792827505 @default.
- W4324360044 cites W2896092083 @default.
- W4324360044 cites W2908320224 @default.
- W4324360044 cites W2951991161 @default.
- W4324360044 cites W3000451586 @default.
- W4324360044 cites W3009942016 @default.
- W4324360044 cites W3012456963 @default.
- W4324360044 cites W3013709343 @default.
- W4324360044 cites W3027201985 @default.
- W4324360044 cites W3027225766 @default.
- W4324360044 cites W3036453075 @default.
- W4324360044 cites W3099503507 @default.
- W4324360044 cites W3104899156 @default.
- W4324360044 cites W3194506987 @default.
- W4324360044 cites W3195032332 @default.
- W4324360044 cites W3210405346 @default.
- W4324360044 cites W4213244977 @default.
- W4324360044 cites W4290755378 @default.
- W4324360044 doi "https://doi.org/10.1016/j.jag.2023.103256" @default.
- W4324360044 hasPublicationYear "2023" @default.
- W4324360044 type Work @default.
- W4324360044 citedByCount "1" @default.
- W4324360044 countsByYear W43243600442023 @default.
- W4324360044 crossrefType "journal-article" @default.
- W4324360044 hasAuthorship W4324360044A5030672015 @default.
- W4324360044 hasAuthorship W4324360044A5043449790 @default.
- W4324360044 hasAuthorship W4324360044A5064639473 @default.
- W4324360044 hasBestOaLocation W43243600441 @default.
- W4324360044 hasConcept C111919701 @default.
- W4324360044 hasConcept C11413529 @default.
- W4324360044 hasConcept C118505674 @default.
- W4324360044 hasConcept C119599485 @default.
- W4324360044 hasConcept C124101348 @default.
- W4324360044 hasConcept C127413603 @default.
- W4324360044 hasConcept C153180895 @default.
- W4324360044 hasConcept C154945302 @default.
- W4324360044 hasConcept C155512373 @default.
- W4324360044 hasConcept C165801399 @default.
- W4324360044 hasConcept C205649164 @default.
- W4324360044 hasConcept C41008148 @default.
- W4324360044 hasConcept C62649853 @default.
- W4324360044 hasConcept C66322947 @default.
- W4324360044 hasConcept C81363708 @default.
- W4324360044 hasConceptScore W4324360044C111919701 @default.
- W4324360044 hasConceptScore W4324360044C11413529 @default.
- W4324360044 hasConceptScore W4324360044C118505674 @default.
- W4324360044 hasConceptScore W4324360044C119599485 @default.
- W4324360044 hasConceptScore W4324360044C124101348 @default.
- W4324360044 hasConceptScore W4324360044C127413603 @default.
- W4324360044 hasConceptScore W4324360044C153180895 @default.
- W4324360044 hasConceptScore W4324360044C154945302 @default.
- W4324360044 hasConceptScore W4324360044C155512373 @default.
- W4324360044 hasConceptScore W4324360044C165801399 @default.
- W4324360044 hasConceptScore W4324360044C205649164 @default.
- W4324360044 hasConceptScore W4324360044C41008148 @default.
- W4324360044 hasConceptScore W4324360044C62649853 @default.
- W4324360044 hasConceptScore W4324360044C66322947 @default.
- W4324360044 hasConceptScore W4324360044C81363708 @default.
- W4324360044 hasFunder F4320321001 @default.
- W4324360044 hasLocation W43243600441 @default.
- W4324360044 hasOpenAccess W4324360044 @default.
- W4324360044 hasPrimaryLocation W43243600441 @default.
- W4324360044 hasRelatedWork W2275988210 @default.
- W4324360044 hasRelatedWork W2521062615 @default.
- W4324360044 hasRelatedWork W2704904180 @default.
- W4324360044 hasRelatedWork W2767651786 @default.
- W4324360044 hasRelatedWork W2782645198 @default.
- W4324360044 hasRelatedWork W2912288872 @default.
- W4324360044 hasRelatedWork W3016958897 @default.
- W4324360044 hasRelatedWork W3181746755 @default.
- W4324360044 hasRelatedWork W4283379348 @default.
- W4324360044 hasRelatedWork W4312417841 @default.
- W4324360044 hasVolume "118" @default.
- W4324360044 isParatext "false" @default.
- W4324360044 isRetracted "false" @default.
- W4324360044 workType "article" @default.