Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367016725> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4367016725 endingPage "5" @default.
- W4367016725 startingPage "1" @default.
- W4367016725 abstract "Benefiting from effective global information interaction, vision-transformers (ViTs) have been widely used in the building extraction task. However, buildings in remote sensing (RS) images usually differ greatly in size. Mainstream ViT-based segmentation models for RS images are based on Swin Transformer, which lacks multi-scale information inside the ViT block. In addition, they only connect the output of the entire ViT encoder block to the decoder, which ignore the similarity information of the attention maps inside the ViT encoder block, and are unable to provide better global dependencies for the decoder. To solve above problems, we introduce a novel Shunted Transformer, which enables the model to capture multi-scale information internally while fully establishing global dependencies, to build a pure ViT-based U-shaped model for building extraction. Furthermore, unlike the previous single-skip-connection structure of U-shaped methods, we build a novel dual skip connection structure inside the model. It simultaneously transmits the attention maps inside the ViT encoder block and its entire output to the decoder, thereby fully mining the information of the ViT encoder block and providing better global information guidance for the decoder. Thus, our model is named Shunted Dual Skip Connection UNet (SDSC-UNet). We also design a feature fusion module called Dual Skip Upsample Fusion Module (DSUFM) to aggregate the information. Our model has yields state-of-the-art (SOTA) performance (83.02%IoU) on the Inria Aerial Image Labeling Dataset. Code will be available." @default.
- W4367016725 created "2023-04-27" @default.
- W4367016725 creator A5058424158 @default.
- W4367016725 creator A5060120202 @default.
- W4367016725 creator A5076850388 @default.
- W4367016725 date "2023-01-01" @default.
- W4367016725 modified "2023-10-14" @default.
- W4367016725 title "SDSC-UNet: Dual Skip Connection ViT-Based U-Shaped Model for Building Extraction" @default.
- W4367016725 cites W1903029394 @default.
- W4367016725 cites W2194775991 @default.
- W4367016725 cites W2908320224 @default.
- W4367016725 cites W2939647427 @default.
- W4367016725 cites W2996327453 @default.
- W4367016725 cites W3014060899 @default.
- W4367016725 cites W3112929693 @default.
- W4367016725 cites W3138516171 @default.
- W4367016725 cites W3161825146 @default.
- W4367016725 cites W3174867596 @default.
- W4367016725 cites W3190334976 @default.
- W4367016725 cites W3204166336 @default.
- W4367016725 cites W3211329537 @default.
- W4367016725 cites W3217005392 @default.
- W4367016725 cites W4214893857 @default.
- W4367016725 cites W4226289601 @default.
- W4367016725 cites W4313160444 @default.
- W4367016725 doi "https://doi.org/10.1109/lgrs.2023.3270303" @default.
- W4367016725 hasPublicationYear "2023" @default.
- W4367016725 type Work @default.
- W4367016725 citedByCount "0" @default.
- W4367016725 crossrefType "journal-article" @default.
- W4367016725 hasAuthorship W4367016725A5058424158 @default.
- W4367016725 hasAuthorship W4367016725A5060120202 @default.
- W4367016725 hasAuthorship W4367016725A5076850388 @default.
- W4367016725 hasConcept C111919701 @default.
- W4367016725 hasConcept C118505674 @default.
- W4367016725 hasConcept C121332964 @default.
- W4367016725 hasConcept C153180895 @default.
- W4367016725 hasConcept C154945302 @default.
- W4367016725 hasConcept C165801399 @default.
- W4367016725 hasConcept C2524010 @default.
- W4367016725 hasConcept C2777210771 @default.
- W4367016725 hasConcept C31972630 @default.
- W4367016725 hasConcept C33923547 @default.
- W4367016725 hasConcept C41008148 @default.
- W4367016725 hasConcept C62520636 @default.
- W4367016725 hasConcept C66322947 @default.
- W4367016725 hasConcept C89600930 @default.
- W4367016725 hasConceptScore W4367016725C111919701 @default.
- W4367016725 hasConceptScore W4367016725C118505674 @default.
- W4367016725 hasConceptScore W4367016725C121332964 @default.
- W4367016725 hasConceptScore W4367016725C153180895 @default.
- W4367016725 hasConceptScore W4367016725C154945302 @default.
- W4367016725 hasConceptScore W4367016725C165801399 @default.
- W4367016725 hasConceptScore W4367016725C2524010 @default.
- W4367016725 hasConceptScore W4367016725C2777210771 @default.
- W4367016725 hasConceptScore W4367016725C31972630 @default.
- W4367016725 hasConceptScore W4367016725C33923547 @default.
- W4367016725 hasConceptScore W4367016725C41008148 @default.
- W4367016725 hasConceptScore W4367016725C62520636 @default.
- W4367016725 hasConceptScore W4367016725C66322947 @default.
- W4367016725 hasConceptScore W4367016725C89600930 @default.
- W4367016725 hasFunder F4320309612 @default.
- W4367016725 hasFunder F4320321001 @default.
- W4367016725 hasFunder F4320321885 @default.
- W4367016725 hasLocation W43670167251 @default.
- W4367016725 hasOpenAccess W4367016725 @default.
- W4367016725 hasPrimaryLocation W43670167251 @default.
- W4367016725 hasRelatedWork W2142795561 @default.
- W4367016725 hasRelatedWork W2322550112 @default.
- W4367016725 hasRelatedWork W2334580170 @default.
- W4367016725 hasRelatedWork W2379948177 @default.
- W4367016725 hasRelatedWork W2384362569 @default.
- W4367016725 hasRelatedWork W2561132942 @default.
- W4367016725 hasRelatedWork W2984576820 @default.
- W4367016725 hasRelatedWork W4205302943 @default.
- W4367016725 hasRelatedWork W2107949441 @default.
- W4367016725 hasRelatedWork W2181948922 @default.
- W4367016725 hasVolume "20" @default.
- W4367016725 isParatext "false" @default.
- W4367016725 isRetracted "false" @default.
- W4367016725 workType "article" @default.