FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376119121> ?p ?o ?g. }

• W4376119121 endingPage "2780" @default.
• W4376119121 startingPage "2754" @default.
• W4376119121 abstract "Convolution in convolutional neural network(CNN) essentially uses a filter (kernel) with shared parameters to achieve feature extraction by computing the weighted sum of the centre pixel and adjacent pixels. The transformer divides the input image into patches and adds position encodings, then learns global semantic information and performs remote modelling through a self-attentive mechanism. However, CNNs are good at extracting local features but have difficulty in capturing global cues; the Transformer uses the self-attention mechanism for remote modelling. However, relative to CNN, local feature details are ignored to a certain extent. We believe that CNN and Transformer are complementary and will show better results if they are fused. Therefore, in this work, we propose a Hybrid Transformer-CNN Networks based on the fusion of CNN and Transformer branches for remote sensing change detection. In the CNN branch, we use the classical U-Net architecture to learn local semantic features. In the Transformer branch, we use Transformer-based progressive sampling to focus the model’s attention on objects of interest and prevent corrupting object structure. Subsequently, we propose an adaptive feature merging module to fully fuse the features of CNN and Transformer to enhance feature representation. At the same time, we introduce a differentiable superpixel branch to take advantage of the superpixel segmentation algorithm to accurately identify object boundaries, preserve boundary information and reduce noise in pixel-level features. We supplement the fused enhanced features into the superpixel branch features using a feature refinement module. After our experiments, we demonstrate the superiority of our model over other State of the art methods." @default.
• W4376119121 created "2023-05-12" @default.
• W4376119121 creator A5028836596 @default.
• W4376119121 creator A5035245548 @default.
• W4376119121 creator A5078116487 @default.
• W4376119121 date "2023-04-18" @default.
• W4376119121 modified "2023-10-10" @default.
• W4376119121 title "Hybrid transformer-CNN networks using superpixel segmentation for remote sensing building change detection" @default.
• W4376119121 cites W1896395893 @default.
• W4376119121 cites W1938929646 @default.
• W4376119121 cites W1978283872 @default.
• W4376119121 cites W1997739364 @default.
• W4376119121 cites W1998595580 @default.
• W4376119121 cites W2003892834 @default.
• W4376119121 cites W2005256556 @default.
• W4376119121 cites W2006383776 @default.
• W4376119121 cites W2007012942 @default.
• W4376119121 cites W2015619014 @default.
• W4376119121 cites W2015780366 @default.
• W4376119121 cites W2017313218 @default.
• W4376119121 cites W2036841511 @default.
• W4376119121 cites W2042709218 @default.
• W4376119121 cites W2051511560 @default.
• W4376119121 cites W2103031616 @default.
• W4376119121 cites W2118246710 @default.
• W4376119121 cites W2134969826 @default.
• W4376119121 cites W2140023211 @default.
• W4376119121 cites W2144552105 @default.
• W4376119121 cites W2172859194 @default.
• W4376119121 cites W2472768686 @default.
• W4376119121 cites W2509917403 @default.
• W4376119121 cites W2883606943 @default.
• W4376119121 cites W2891248708 @default.
• W4376119121 cites W2894660140 @default.
• W4376119121 cites W2896365540 @default.
• W4376119121 cites W2908320224 @default.
• W4376119121 cites W2918277739 @default.
• W4376119121 cites W2990228562 @default.
• W4376119121 cites W3027225766 @default.
• W4376119121 cites W3036453075 @default.
• W4376119121 cites W3037640242 @default.
• W4376119121 cites W3104899156 @default.
• W4376119121 cites W3119456559 @default.
• W4376119121 cites W3120467244 @default.
• W4376119121 cites W3138516171 @default.
• W4376119121 cites W3157062364 @default.
• W4376119121 cites W3160694286 @default.
• W4376119121 cites W3178882511 @default.
• W4376119121 cites W3209695792 @default.
• W4376119121 cites W3211465673 @default.
• W4376119121 cites W4226291728 @default.
• W4376119121 cites W4290079400 @default.
• W4376119121 cites W4292348075 @default.
• W4376119121 cites W4312549298 @default.
• W4376119121 cites W4313029572 @default.
• W4376119121 cites W4366147336 @default.
• W4376119121 doi "https://doi.org/10.1080/01431161.2023.2208711" @default.
• W4376119121 hasPublicationYear "2023" @default.
• W4376119121 type Work @default.
• W4376119121 citedByCount "4" @default.
• W4376119121 countsByYear W43761191212023 @default.
• W4376119121 crossrefType "journal-article" @default.
• W4376119121 hasAuthorship W4376119121A5028836596 @default.
• W4376119121 hasAuthorship W4376119121A5035245548 @default.
• W4376119121 hasAuthorship W4376119121A5078116487 @default.
• W4376119121 hasConcept C121332964 @default.
• W4376119121 hasConcept C153180895 @default.
• W4376119121 hasConcept C154945302 @default.
• W4376119121 hasConcept C160633673 @default.
• W4376119121 hasConcept C165801399 @default.
• W4376119121 hasConcept C31972630 @default.
• W4376119121 hasConcept C41008148 @default.
• W4376119121 hasConcept C52622490 @default.
• W4376119121 hasConcept C62520636 @default.
• W4376119121 hasConcept C66322947 @default.
• W4376119121 hasConcept C81363708 @default.
• W4376119121 hasConcept C89600930 @default.
• W4376119121 hasConceptScore W4376119121C121332964 @default.
• W4376119121 hasConceptScore W4376119121C153180895 @default.
• W4376119121 hasConceptScore W4376119121C154945302 @default.
• W4376119121 hasConceptScore W4376119121C160633673 @default.
• W4376119121 hasConceptScore W4376119121C165801399 @default.
• W4376119121 hasConceptScore W4376119121C31972630 @default.
• W4376119121 hasConceptScore W4376119121C41008148 @default.
• W4376119121 hasConceptScore W4376119121C52622490 @default.
• W4376119121 hasConceptScore W4376119121C62520636 @default.
• W4376119121 hasConceptScore W4376119121C66322947 @default.
• W4376119121 hasConceptScore W4376119121C81363708 @default.
• W4376119121 hasConceptScore W4376119121C89600930 @default.
• W4376119121 hasFunder F4320321001 @default.
• W4376119121 hasIssue "8" @default.
• W4376119121 hasLocation W43761191211 @default.
• W4376119121 hasOpenAccess W4376119121 @default.
• W4376119121 hasPrimaryLocation W43761191211 @default.
• W4376119121 hasRelatedWork W121273120 @default.
• W4376119121 hasRelatedWork W1669643531 @default.
• W4376119121 hasRelatedWork W2005437358 @default.
• W4376119121 hasRelatedWork W2008656436 @default.

• next