Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386824701> ?p ?o ?g. }
- W4386824701 endingPage "5269" @default.
- W4386824701 startingPage "5257" @default.
- W4386824701 abstract "Existing methods for Salient Object Detection in Optical Remote Sensing Images (ORSI-SOD) mainly adopt Convolutional Neural Networks (CNNs) as the backbone, such as VGG and ResNet. Since CNNs can only extract features within certain receptive fields, most ORSI-SOD methods generally follow the local-to-contextual paradigm. In this paper, we propose a novel Global Extraction Local Exploration Network (GeleNet) for ORSI-SOD following the global-to-local paradigm. Specifically, GeleNet first adopts a transformer backbone to generate four-level feature embeddings with global long-range dependencies. Then, GeleNet employs a Direction-aware Shuffle Weighted Spatial Attention Module (D-SWSAM) and its simplified version (SWSAM) to enhance local interactions, and a Knowledge Transfer Module (KTM) to further enhance cross-level contextual interactions. D-SWSAM comprehensively perceives the orientation information in the lowest-level features through directional convolutions to adapt to various orientations of salient objects in ORSIs, and effectively enhances the details of salient objects with an improved attention mechanism. SWSAM discards the direction-aware part of D-SWSAM to focus on localizing salient objects in the highest-level features. KTM models the contextual correlation knowledge of two middle-level features of different scales based on the self-attention mechanism, and transfers the knowledge to the raw features to generate more discriminative features. Finally, a saliency predictor is used to generate the saliency map based on the outputs of the above three modules. Extensive experiments on three public datasets demonstrate that the proposed GeleNet outperforms relevant state-of-the-art methods. The code and results of our method are available at https://github.com/MathLee/GeleNet." @default.
- W4386824701 created "2023-09-19" @default.
- W4386824701 creator A5032336491 @default.
- W4386824701 creator A5040009629 @default.
- W4386824701 creator A5061140967 @default.
- W4386824701 creator A5061469520 @default.
- W4386824701 creator A5062627263 @default.
- W4386824701 date "2023-01-01" @default.
- W4386824701 modified "2023-10-15" @default.
- W4386824701 title "Salient Object Detection in Optical Remote Sensing Images Driven by Transformer" @default.
- W4386824701 cites W1677182931 @default.
- W4386824701 cites W1978479866 @default.
- W4386824701 cites W2100470808 @default.
- W4386824701 cites W2147800946 @default.
- W4386824701 cites W2194775991 @default.
- W4386824701 cites W2323509952 @default.
- W4386824701 cites W2793668851 @default.
- W4386824701 cites W2807746031 @default.
- W4386824701 cites W2912465472 @default.
- W4386824701 cites W2939217524 @default.
- W4386824701 cites W2955058313 @default.
- W4386824701 cites W2961348656 @default.
- W4386824701 cites W2963112696 @default.
- W4386824701 cites W2963125010 @default.
- W4386824701 cites W2963420686 @default.
- W4386824701 cites W2963529609 @default.
- W4386824701 cites W2963868681 @default.
- W4386824701 cites W2971137300 @default.
- W4386824701 cites W2981374717 @default.
- W4386824701 cites W2985335644 @default.
- W4386824701 cites W2990984982 @default.
- W4386824701 cites W2997316506 @default.
- W4386824701 cites W3003121299 @default.
- W4386824701 cites W3010616503 @default.
- W4386824701 cites W3010722397 @default.
- W4386824701 cites W3019728440 @default.
- W4386824701 cites W3029368604 @default.
- W4386824701 cites W3034552520 @default.
- W4386824701 cites W3035290198 @default.
- W4386824701 cites W3035422681 @default.
- W4386824701 cites W3084740725 @default.
- W4386824701 cites W3102864715 @default.
- W4386824701 cites W3104979525 @default.
- W4386824701 cites W3106587394 @default.
- W4386824701 cites W3108948422 @default.
- W4386824701 cites W3109623941 @default.
- W4386824701 cites W3112885960 @default.
- W4386824701 cites W3121523901 @default.
- W4386824701 cites W3125703990 @default.
- W4386824701 cites W3131500599 @default.
- W4386824701 cites W3132018008 @default.
- W4386824701 cites W3135874576 @default.
- W4386824701 cites W3136838953 @default.
- W4386824701 cites W3138516171 @default.
- W4386824701 cites W3162418282 @default.
- W4386824701 cites W3166714471 @default.
- W4386824701 cites W3173382343 @default.
- W4386824701 cites W3175515048 @default.
- W4386824701 cites W3175617055 @default.
- W4386824701 cites W3179147540 @default.
- W4386824701 cites W3188023301 @default.
- W4386824701 cites W3199185814 @default.
- W4386824701 cites W3203699578 @default.
- W4386824701 cites W3207668590 @default.
- W4386824701 cites W3208937872 @default.
- W4386824701 cites W3212645988 @default.
- W4386824701 cites W3217306379 @default.
- W4386824701 cites W4205288538 @default.
- W4386824701 cites W4206947033 @default.
- W4386824701 cites W4214561053 @default.
- W4386824701 cites W4221138999 @default.
- W4386824701 cites W4226537900 @default.
- W4386824701 cites W4285161446 @default.
- W4386824701 cites W4296913506 @default.
- W4386824701 cites W4307778795 @default.
- W4386824701 cites W4312373555 @default.
- W4386824701 cites W4315631877 @default.
- W4386824701 doi "https://doi.org/10.1109/tip.2023.3314285" @default.
- W4386824701 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37721873" @default.
- W4386824701 hasPublicationYear "2023" @default.
- W4386824701 type Work @default.
- W4386824701 citedByCount "0" @default.
- W4386824701 crossrefType "journal-article" @default.
- W4386824701 hasAuthorship W4386824701A5032336491 @default.
- W4386824701 hasAuthorship W4386824701A5040009629 @default.
- W4386824701 hasAuthorship W4386824701A5061140967 @default.
- W4386824701 hasAuthorship W4386824701A5061469520 @default.
- W4386824701 hasAuthorship W4386824701A5062627263 @default.
- W4386824701 hasBestOaLocation W43868247012 @default.
- W4386824701 hasConcept C153180895 @default.
- W4386824701 hasConcept C154945302 @default.
- W4386824701 hasConcept C2776151529 @default.
- W4386824701 hasConcept C2780719617 @default.
- W4386824701 hasConcept C31972630 @default.
- W4386824701 hasConcept C41008148 @default.
- W4386824701 hasConcept C52622490 @default.
- W4386824701 hasConcept C59404180 @default.
- W4386824701 hasConcept C81363708 @default.