Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385819971> ?p ?o ?g. }
- W4385819971 endingPage "14" @default.
- W4385819971 startingPage "1" @default.
- W4385819971 abstract "Despite the remarkable progress made by the salient object detection of natural sensing images (NSI-SOD), the complex background and scale diversity issues of remote sensing images (RSIs) still pose a substantial obstacle. In this study, we build an end-to-end channel-enhanced remodeling-based network (CRNet) for optical RSIs (ORSIs) to highlight salient objects through feature augmentation. First, the backbone convolutional block is used to suggest the fundamental characteristics. Then, we use the channel enhance module (CEM) to enhance the shallow features. CEM primarily relies on the channel attention mechanism and employs a no-downscaling strategy to produce local cross-channel interaction, which lowers model complexity while enhancing extraction performance. Meanwhile, we use the redefined feature module (RFM) to reconstruct the deep features and generate global attention features by dimensional transformation and feature relationship aggregation to achieve the role of locating salient targets. Finally, the cascade combines the multi-scale features to provide the final saliency map. To further enhance the representational power of the network, we use a hybrid loss function to improve performance. The proposed approach outperforms current state-of-the-art methods, as shown by several experiments on three available datasets. The source code of the proposed CRNet is available publicly at https://github.com/hilitteq/CRNet.git." @default.
- W4385819971 created "2023-08-15" @default.
- W4385819971 creator A5031361250 @default.
- W4385819971 creator A5059068224 @default.
- W4385819971 creator A5072315367 @default.
- W4385819971 creator A5074218052 @default.
- W4385819971 creator A5074587654 @default.
- W4385819971 creator A5087119507 @default.
- W4385819971 creator A5087729203 @default.
- W4385819971 date "2023-01-01" @default.
- W4385819971 modified "2023-10-16" @default.
- W4385819971 title "CRNet: Channel-enhanced Remodeling-based Network for Salient Object Detection in Optical Remote Sensing Images" @default.
- W4385819971 cites W2070083314 @default.
- W4385819971 cites W2158535435 @default.
- W4385819971 cites W2160398355 @default.
- W4385819971 cites W2293542025 @default.
- W4385819971 cites W2346506533 @default.
- W4385819971 cites W2518599539 @default.
- W4385819971 cites W2744876417 @default.
- W4385819971 cites W2757094569 @default.
- W4385819971 cites W2762270259 @default.
- W4385819971 cites W2780708736 @default.
- W4385819971 cites W2783165089 @default.
- W4385819971 cites W2783231089 @default.
- W4385819971 cites W2791979332 @default.
- W4385819971 cites W2792965491 @default.
- W4385819971 cites W2793268137 @default.
- W4385819971 cites W2799074129 @default.
- W4385819971 cites W2800822850 @default.
- W4385819971 cites W2890795004 @default.
- W4385819971 cites W2928165649 @default.
- W4385819971 cites W2939217524 @default.
- W4385819971 cites W2944053494 @default.
- W4385819971 cites W2945874778 @default.
- W4385819971 cites W2948500402 @default.
- W4385819971 cites W2961348656 @default.
- W4385819971 cites W2963112696 @default.
- W4385819971 cites W2963299740 @default.
- W4385819971 cites W2963706010 @default.
- W4385819971 cites W2963868681 @default.
- W4385819971 cites W2963881378 @default.
- W4385819971 cites W2989161706 @default.
- W4385819971 cites W2990984982 @default.
- W4385819971 cites W2999756127 @default.
- W4385819971 cites W3022643044 @default.
- W4385819971 cites W3022710784 @default.
- W4385819971 cites W3035422681 @default.
- W4385819971 cites W3084740725 @default.
- W4385819971 cites W3100011500 @default.
- W4385819971 cites W3102864715 @default.
- W4385819971 cites W3104979525 @default.
- W4385819971 cites W3108948422 @default.
- W4385819971 cites W3135874576 @default.
- W4385819971 cites W3166518554 @default.
- W4385819971 cites W3179147540 @default.
- W4385819971 cites W3188023301 @default.
- W4385819971 cites W3208677626 @default.
- W4385819971 cites W3208937872 @default.
- W4385819971 cites W3209011308 @default.
- W4385819971 cites W3217306379 @default.
- W4385819971 cites W4205457644 @default.
- W4385819971 cites W4221014685 @default.
- W4385819971 cites W4226537900 @default.
- W4385819971 cites W4285301526 @default.
- W4385819971 cites W4289641562 @default.
- W4385819971 doi "https://doi.org/10.1109/tgrs.2023.3305021" @default.
- W4385819971 hasPublicationYear "2023" @default.
- W4385819971 type Work @default.
- W4385819971 citedByCount "0" @default.
- W4385819971 crossrefType "journal-article" @default.
- W4385819971 hasAuthorship W4385819971A5031361250 @default.
- W4385819971 hasAuthorship W4385819971A5059068224 @default.
- W4385819971 hasAuthorship W4385819971A5072315367 @default.
- W4385819971 hasAuthorship W4385819971A5074218052 @default.
- W4385819971 hasAuthorship W4385819971A5074587654 @default.
- W4385819971 hasAuthorship W4385819971A5087119507 @default.
- W4385819971 hasAuthorship W4385819971A5087729203 @default.
- W4385819971 hasConcept C127162648 @default.
- W4385819971 hasConcept C127313418 @default.
- W4385819971 hasConcept C138885662 @default.
- W4385819971 hasConcept C153180895 @default.
- W4385819971 hasConcept C154945302 @default.
- W4385819971 hasConcept C177264268 @default.
- W4385819971 hasConcept C199360897 @default.
- W4385819971 hasConcept C2524010 @default.
- W4385819971 hasConcept C2776151529 @default.
- W4385819971 hasConcept C2776401178 @default.
- W4385819971 hasConcept C2776760102 @default.
- W4385819971 hasConcept C2777210771 @default.
- W4385819971 hasConcept C2780719617 @default.
- W4385819971 hasConcept C31972630 @default.
- W4385819971 hasConcept C33923547 @default.
- W4385819971 hasConcept C41008148 @default.
- W4385819971 hasConcept C41895202 @default.
- W4385819971 hasConcept C52622490 @default.
- W4385819971 hasConcept C62649853 @default.
- W4385819971 hasConcept C76155785 @default.
- W4385819971 hasConcept C88796919 @default.