Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385945169> ?p ?o ?g. }
- W4385945169 endingPage "18" @default.
- W4385945169 startingPage "1" @default.
- W4385945169 abstract "The U-Net-like model has been widely studied in the field of building extraction. However, most of these models are based on locally sensed Convolutional Neural Networks(CNNs) designed with symmetric structure and single feature processing, which cannot accurately identify buildings with different sizes, shapes, and colors in remote sensing images. To overcome these problems, we propose the asymmetric cascade fusion network(ACFN), based on the Vision Transformer(ViT), to design a novel asymmetric architecture to recognize buildings of different sizes and shapes by processing multi-granularity features by different means. First, the asymmetric architecture obtains multi-granularity features with global contextual information by embedding different types of attention in encoder-decoders of different sizes. This architecture can identify densely distributed and occluded buildings by semantic reasoning in remote sensing images with complex information. Second, we design a multi-branch weighted pyramid pooling module, which sets different branch weights to offset the background noise introduced in introducing global contextual information. Our ACFN significantly improves the Beijing buildings, ISPRS-Vaihingen, and LoveDA datasets." @default.
- W4385945169 created "2023-08-18" @default.
- W4385945169 creator A5003029072 @default.
- W4385945169 creator A5007813793 @default.
- W4385945169 creator A5010168982 @default.
- W4385945169 creator A5034394648 @default.
- W4385945169 creator A5059752625 @default.
- W4385945169 creator A5084093126 @default.
- W4385945169 date "2023-01-01" @default.
- W4385945169 modified "2023-10-17" @default.
- W4385945169 title "Asymmetric Cascade Fusion Network for Building Extraction" @default.
- W4385945169 cites W1903029394 @default.
- W4385945169 cites W2031489346 @default.
- W4385945169 cites W2097117768 @default.
- W4385945169 cites W2102673432 @default.
- W4385945169 cites W2105101328 @default.
- W4385945169 cites W2106996050 @default.
- W4385945169 cites W2108598243 @default.
- W4385945169 cites W2125911428 @default.
- W4385945169 cites W2141200610 @default.
- W4385945169 cites W2151502878 @default.
- W4385945169 cites W2194775991 @default.
- W4385945169 cites W2340897893 @default.
- W4385945169 cites W2412782625 @default.
- W4385945169 cites W2560023338 @default.
- W4385945169 cites W2565639579 @default.
- W4385945169 cites W2618530766 @default.
- W4385945169 cites W2737258237 @default.
- W4385945169 cites W2771784662 @default.
- W4385945169 cites W2884822772 @default.
- W4385945169 cites W2886934227 @default.
- W4385945169 cites W2908320224 @default.
- W4385945169 cites W2916798096 @default.
- W4385945169 cites W2963091558 @default.
- W4385945169 cites W2963881378 @default.
- W4385945169 cites W2981689412 @default.
- W4385945169 cites W3003394660 @default.
- W4385945169 cites W3014060899 @default.
- W4385945169 cites W3023329043 @default.
- W4385945169 cites W3053564872 @default.
- W4385945169 cites W3122259118 @default.
- W4385945169 cites W3131500599 @default.
- W4385945169 cites W3138516171 @default.
- W4385945169 cites W3161300377 @default.
- W4385945169 cites W3168495321 @default.
- W4385945169 cites W3170841864 @default.
- W4385945169 cites W3172435473 @default.
- W4385945169 cites W3184324897 @default.
- W4385945169 cites W3202923600 @default.
- W4385945169 cites W3216720075 @default.
- W4385945169 cites W4206383524 @default.
- W4385945169 cites W4210736635 @default.
- W4385945169 cites W4225088723 @default.
- W4385945169 cites W4226280350 @default.
- W4385945169 cites W4226289601 @default.
- W4385945169 cites W4226334005 @default.
- W4385945169 cites W4281951604 @default.
- W4385945169 cites W4293680532 @default.
- W4385945169 cites W4312273141 @default.
- W4385945169 cites W4312443924 @default.
- W4385945169 cites W4313160444 @default.
- W4385945169 cites W4381232908 @default.
- W4385945169 doi "https://doi.org/10.1109/tgrs.2023.3306018" @default.
- W4385945169 hasPublicationYear "2023" @default.
- W4385945169 type Work @default.
- W4385945169 citedByCount "0" @default.
- W4385945169 crossrefType "journal-article" @default.
- W4385945169 hasAuthorship W4385945169A5003029072 @default.
- W4385945169 hasAuthorship W4385945169A5007813793 @default.
- W4385945169 hasAuthorship W4385945169A5010168982 @default.
- W4385945169 hasAuthorship W4385945169A5034394648 @default.
- W4385945169 hasAuthorship W4385945169A5059752625 @default.
- W4385945169 hasAuthorship W4385945169A5084093126 @default.
- W4385945169 hasConcept C111919701 @default.
- W4385945169 hasConcept C118505674 @default.
- W4385945169 hasConcept C120665830 @default.
- W4385945169 hasConcept C121332964 @default.
- W4385945169 hasConcept C123657996 @default.
- W4385945169 hasConcept C124101348 @default.
- W4385945169 hasConcept C142575187 @default.
- W4385945169 hasConcept C153180895 @default.
- W4385945169 hasConcept C154945302 @default.
- W4385945169 hasConcept C166957645 @default.
- W4385945169 hasConcept C175291020 @default.
- W4385945169 hasConcept C177774035 @default.
- W4385945169 hasConcept C185592680 @default.
- W4385945169 hasConcept C199360897 @default.
- W4385945169 hasConcept C205649164 @default.
- W4385945169 hasConcept C31972630 @default.
- W4385945169 hasConcept C34146451 @default.
- W4385945169 hasConcept C41008148 @default.
- W4385945169 hasConcept C43617362 @default.
- W4385945169 hasConcept C52622490 @default.
- W4385945169 hasConcept C62649853 @default.
- W4385945169 hasConcept C70437156 @default.
- W4385945169 hasConcept C81363708 @default.
- W4385945169 hasConcept C9770341 @default.
- W4385945169 hasConceptScore W4385945169C111919701 @default.