Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380997032> ?p ?o ?g. }
- W4380997032 endingPage "109152" @default.
- W4380997032 startingPage "109152" @default.
- W4380997032 abstract "Remote sensing image (RSIs) segmentation is widely used in urban planning, natural disaster detection and many other fields. Compared with natural scene images, RSIs have higher resolution, complex imaging, and diverse object shapes and sizes, while semantic segmentation methods based on deep learning often require many data labels. In this paper, we propose a semi-supervised RSIs segmentation network with multi-scale deformable threshold feature extraction module and mixed attention (MDMANet). First, a pyramid ensemble structure is used, which incorporates deformable convolution and bole convolution, to extract features of objects with different shapes and sizes and reduce the influence of redundant features. Meanwhile, a mixed attention (MA) is proposed to aggregate long-range contextual relationships and fuse low-level features with high-level features. Second, an FCN-based full convolution discriminator task network is designed to help evaluate the feasibility of unlabeled image prediction results. We performed experimental validation on three datasets, and the results show that MDMANet segmentation provides more significant improvement in accuracy and better generalization than existing segmentation networks." @default.
- W4380997032 created "2023-06-17" @default.
- W4380997032 creator A5000858657 @default.
- W4380997032 creator A5001305383 @default.
- W4380997032 creator A5010726528 @default.
- W4380997032 creator A5022832205 @default.
- W4380997032 creator A5069963947 @default.
- W4380997032 creator A5072820730 @default.
- W4380997032 creator A5076714108 @default.
- W4380997032 creator A5080071103 @default.
- W4380997032 creator A5090470209 @default.
- W4380997032 date "2023-11-01" @default.
- W4380997032 modified "2023-09-27" @default.
- W4380997032 title "MDMASNet: A dual-task interactive semi-supervised remote sensing image segmentation method" @default.
- W4380997032 cites W1991525235 @default.
- W4380997032 cites W2151103935 @default.
- W4380997032 cites W2767943769 @default.
- W4380997032 cites W2886397424 @default.
- W4380997032 cites W2902190145 @default.
- W4380997032 cites W2911043813 @default.
- W4380997032 cites W2944418962 @default.
- W4380997032 cites W2963881378 @default.
- W4380997032 cites W2965521953 @default.
- W4380997032 cites W2995766874 @default.
- W4380997032 cites W3007268491 @default.
- W4380997032 cites W3014120959 @default.
- W4380997032 cites W3019659794 @default.
- W4380997032 cites W3026303927 @default.
- W4380997032 cites W3047443805 @default.
- W4380997032 cites W3048631361 @default.
- W4380997032 cites W3087353686 @default.
- W4380997032 cites W3096831136 @default.
- W4380997032 cites W3102401868 @default.
- W4380997032 cites W3103092912 @default.
- W4380997032 cites W3103993493 @default.
- W4380997032 cites W3111050907 @default.
- W4380997032 cites W3162977387 @default.
- W4380997032 cites W3209745495 @default.
- W4380997032 cites W4210546526 @default.
- W4380997032 cites W4288391619 @default.
- W4380997032 cites W4292057435 @default.
- W4380997032 cites W4319014159 @default.
- W4380997032 doi "https://doi.org/10.1016/j.sigpro.2023.109152" @default.
- W4380997032 hasPublicationYear "2023" @default.
- W4380997032 type Work @default.
- W4380997032 citedByCount "0" @default.
- W4380997032 crossrefType "journal-article" @default.
- W4380997032 hasAuthorship W4380997032A5000858657 @default.
- W4380997032 hasAuthorship W4380997032A5001305383 @default.
- W4380997032 hasAuthorship W4380997032A5010726528 @default.
- W4380997032 hasAuthorship W4380997032A5022832205 @default.
- W4380997032 hasAuthorship W4380997032A5069963947 @default.
- W4380997032 hasAuthorship W4380997032A5072820730 @default.
- W4380997032 hasAuthorship W4380997032A5076714108 @default.
- W4380997032 hasAuthorship W4380997032A5080071103 @default.
- W4380997032 hasAuthorship W4380997032A5090470209 @default.
- W4380997032 hasConcept C119599485 @default.
- W4380997032 hasConcept C124504099 @default.
- W4380997032 hasConcept C127413603 @default.
- W4380997032 hasConcept C134306372 @default.
- W4380997032 hasConcept C138885662 @default.
- W4380997032 hasConcept C141353440 @default.
- W4380997032 hasConcept C142575187 @default.
- W4380997032 hasConcept C146978453 @default.
- W4380997032 hasConcept C153180895 @default.
- W4380997032 hasConcept C154945302 @default.
- W4380997032 hasConcept C177148314 @default.
- W4380997032 hasConcept C201995342 @default.
- W4380997032 hasConcept C204323151 @default.
- W4380997032 hasConcept C205649164 @default.
- W4380997032 hasConcept C2524010 @default.
- W4380997032 hasConcept C2776401178 @default.
- W4380997032 hasConcept C2779803651 @default.
- W4380997032 hasConcept C2780451532 @default.
- W4380997032 hasConcept C31972630 @default.
- W4380997032 hasConcept C33923547 @default.
- W4380997032 hasConcept C41008148 @default.
- W4380997032 hasConcept C41895202 @default.
- W4380997032 hasConcept C45347329 @default.
- W4380997032 hasConcept C50644808 @default.
- W4380997032 hasConcept C52622490 @default.
- W4380997032 hasConcept C62649853 @default.
- W4380997032 hasConcept C65885262 @default.
- W4380997032 hasConcept C76155785 @default.
- W4380997032 hasConcept C89600930 @default.
- W4380997032 hasConcept C94915269 @default.
- W4380997032 hasConceptScore W4380997032C119599485 @default.
- W4380997032 hasConceptScore W4380997032C124504099 @default.
- W4380997032 hasConceptScore W4380997032C127413603 @default.
- W4380997032 hasConceptScore W4380997032C134306372 @default.
- W4380997032 hasConceptScore W4380997032C138885662 @default.
- W4380997032 hasConceptScore W4380997032C141353440 @default.
- W4380997032 hasConceptScore W4380997032C142575187 @default.
- W4380997032 hasConceptScore W4380997032C146978453 @default.
- W4380997032 hasConceptScore W4380997032C153180895 @default.
- W4380997032 hasConceptScore W4380997032C154945302 @default.
- W4380997032 hasConceptScore W4380997032C177148314 @default.
- W4380997032 hasConceptScore W4380997032C201995342 @default.