Matches in SemOpenAlex for { <https://semopenalex.org/work/W4292258096> ?p ?o ?g. }
- W4292258096 endingPage "6956" @default.
- W4292258096 startingPage "6943" @default.
- W4292258096 abstract "Semantic segmentation of high-resolution aerial images is a challenging task on account of inter-class homogeneity and intra-class heterogeneity of land cover. Recent works have sought to mitigate this issue by exploiting pixel-wise global contextual information using self-attention mechanism. However, the existing attention-based methods usually generate inaccurate object boundary segmentation results, as the self-attention model is embedded in high-level features with low resolution due to prohibitively computational complexity. Moreover, existing attention-based models ignore class-wise contextual information from intermediate results, which leads to undesirable feature separability. To obtain discriminative feature as well as generate accurate segmentation boundaries, we present a novel segmentation framework, named Cascade Class-aware Enhanced Network (CCENet) for high resolution aerial imagery. The proposed CCENet predicts segmentation results on multiple stages, and the result of the previous stage is used to refine object boundary details for the latter stage. To exploit the class-aware prior information in previous stage, we propose a lightweight Class-aware Enhanced Module (CaEM) to grab the class-aware contextual dependencies. Specifically, CaEM first extract a set of class representation of the land covers by Global Class Pooling (GCP) block, then reconstruct enhanced feature using Class Relation Measurement (CRM), which alleviates the inter-class homogeneity and intra-class heterogeneity of ground objects in feature space. Quantitative and qualitative experimental results on three publicly available datasets demonstrate the superiority of our CCENet over other state-of-the-art methods in the items of high labelling accuracy and computation efficiency." @default.
- W4292258096 created "2022-08-19" @default.
- W4292258096 creator A5024164148 @default.
- W4292258096 creator A5031045789 @default.
- W4292258096 creator A5068122673 @default.
- W4292258096 creator A5072050541 @default.
- W4292258096 creator A5078725248 @default.
- W4292258096 date "2022-01-01" @default.
- W4292258096 modified "2023-10-01" @default.
- W4292258096 title "CCENet: Cascade Class-Aware Enhanced Network for High-Resolution Aerial Imagery Semantic Segmentation" @default.
- W4292258096 cites W1677182931 @default.
- W4292258096 cites W1903029394 @default.
- W4292258096 cites W1963860205 @default.
- W4292258096 cites W1975258031 @default.
- W4292258096 cites W2194775991 @default.
- W4292258096 cites W2265756958 @default.
- W4292258096 cites W2412782625 @default.
- W4292258096 cites W2560023338 @default.
- W4292258096 cites W2563705555 @default.
- W4292258096 cites W2598666589 @default.
- W4292258096 cites W2618530766 @default.
- W4292258096 cites W2778539913 @default.
- W4292258096 cites W2782475589 @default.
- W4292258096 cites W2789894132 @default.
- W4292258096 cites W2955058313 @default.
- W4292258096 cites W2962870549 @default.
- W4292258096 cites W2963091558 @default.
- W4292258096 cites W2963881378 @default.
- W4292258096 cites W2963995737 @default.
- W4292258096 cites W2964105864 @default.
- W4292258096 cites W2964292098 @default.
- W4292258096 cites W2965383240 @default.
- W4292258096 cites W2967731069 @default.
- W4292258096 cites W2981899103 @default.
- W4292258096 cites W2985459778 @default.
- W4292258096 cites W2990775046 @default.
- W4292258096 cites W2993235622 @default.
- W4292258096 cites W2996322457 @default.
- W4292258096 cites W3009297390 @default.
- W4292258096 cites W3018169007 @default.
- W4292258096 cites W3034427230 @default.
- W4292258096 cites W3034438741 @default.
- W4292258096 cites W3044776120 @default.
- W4292258096 cites W3048753792 @default.
- W4292258096 cites W3089769990 @default.
- W4292258096 cites W3099663315 @default.
- W4292258096 cites W3102850314 @default.
- W4292258096 cites W3105127913 @default.
- W4292258096 cites W3109301572 @default.
- W4292258096 cites W3138136606 @default.
- W4292258096 cites W3165745140 @default.
- W4292258096 cites W3168495321 @default.
- W4292258096 cites W3183174367 @default.
- W4292258096 cites W3194371117 @default.
- W4292258096 cites W3205944634 @default.
- W4292258096 doi "https://doi.org/10.1109/jstars.2022.3199459" @default.
- W4292258096 hasPublicationYear "2022" @default.
- W4292258096 type Work @default.
- W4292258096 citedByCount "1" @default.
- W4292258096 countsByYear W42922580962023 @default.
- W4292258096 crossrefType "journal-article" @default.
- W4292258096 hasAuthorship W4292258096A5024164148 @default.
- W4292258096 hasAuthorship W4292258096A5031045789 @default.
- W4292258096 hasAuthorship W4292258096A5068122673 @default.
- W4292258096 hasAuthorship W4292258096A5072050541 @default.
- W4292258096 hasAuthorship W4292258096A5078725248 @default.
- W4292258096 hasBestOaLocation W42922580961 @default.
- W4292258096 hasConcept C153180895 @default.
- W4292258096 hasConcept C154945302 @default.
- W4292258096 hasConcept C31972630 @default.
- W4292258096 hasConcept C41008148 @default.
- W4292258096 hasConcept C70437156 @default.
- W4292258096 hasConcept C89600930 @default.
- W4292258096 hasConcept C97931131 @default.
- W4292258096 hasConceptScore W4292258096C153180895 @default.
- W4292258096 hasConceptScore W4292258096C154945302 @default.
- W4292258096 hasConceptScore W4292258096C31972630 @default.
- W4292258096 hasConceptScore W4292258096C41008148 @default.
- W4292258096 hasConceptScore W4292258096C70437156 @default.
- W4292258096 hasConceptScore W4292258096C89600930 @default.
- W4292258096 hasConceptScore W4292258096C97931131 @default.
- W4292258096 hasFunder F4320321001 @default.
- W4292258096 hasLocation W42922580961 @default.
- W4292258096 hasLocation W42922580962 @default.
- W4292258096 hasOpenAccess W4292258096 @default.
- W4292258096 hasPrimaryLocation W42922580961 @default.
- W4292258096 hasRelatedWork W1669643531 @default.
- W4292258096 hasRelatedWork W2005437358 @default.
- W4292258096 hasRelatedWork W2024160000 @default.
- W4292258096 hasRelatedWork W2043075591 @default.
- W4292258096 hasRelatedWork W2061273563 @default.
- W4292258096 hasRelatedWork W2517104666 @default.
- W4292258096 hasRelatedWork W2729514902 @default.
- W4292258096 hasRelatedWork W2773500201 @default.
- W4292258096 hasRelatedWork W4287995534 @default.
- W4292258096 hasRelatedWork W2073139667 @default.
- W4292258096 hasVolume "15" @default.
- W4292258096 isParatext "false" @default.