FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380789068> ?p ?o ?g. }

• W4380789068 endingPage "3121" @default.
• W4380789068 startingPage "3121" @default.
• W4380789068 abstract "Water body extraction is a typical task in the semantic segmentation of remote sensing images (RSIs). Deep convolutional neural networks (DCNNs) outperform traditional methods in mining visual features; however, due to the inherent convolutional mechanism of the network, spatial details and abstract semantic representations at different levels are difficult to capture accurately at the same time, and then the extraction results decline to become suboptimal, especially on narrow areas and boundaries. To address the above-mentioned problem, a multiscale successive attention fusion network, named MSAFNet, is proposed to efficiently aggregate the multiscale features from two aspects. A successive attention fusion module (SAFM) is first devised to extract multiscale and fine-grained features of water bodies, while a joint attention module (JAM) is proposed to further mine salient semantic information by jointly modeling contextual dependencies. Furthermore, the multi-level features extracted by the above-mentioned modules are aggregated by a feature fusion module (FFM) so that the edges of water bodies are well mapped, directly improving the segmentation of various water bodies. Extensive experiments were conducted on the Qinghai-Tibet Plateau Lake (QTPL) and the Land-cOVEr Domain Adaptive semantic segmentation (LoveDA) datasets. Numerically, MSAFNet reached the highest accuracy on both QTPL and LoveDA datasets, including Kappa, MIoU, FWIoU, F1, and OA, outperforming several mainstream methods. Regarding the QTPL dataset, MSAFNet peaked at 99.14% and 98.97% in terms of F1 and OA. Although the LoveDA dataset is more challenging, MSAFNet retained the best performance, with F1 and OA being 97.69% and 95.87%. Additionally, visual inspections exhibited consistency with numerical evaluations." @default.
• W4380789068 created "2023-06-16" @default.
• W4380789068 creator A5001865876 @default.
• W4380789068 creator A5017142254 @default.
• W4380789068 creator A5053687089 @default.
• W4380789068 creator A5060642323 @default.
• W4380789068 creator A5071995587 @default.
• W4380789068 creator A5083115565 @default.
• W4380789068 date "2023-06-15" @default.
• W4380789068 modified "2023-09-26" @default.
• W4380789068 title "MSAFNet: Multiscale Successive Attention Fusion Network for Water Body Extraction of Remote Sensing Images" @default.
• W4380789068 cites W1901129140 @default.
• W4380789068 cites W1995581599 @default.
• W4380789068 cites W2009235968 @default.
• W4380789068 cites W2017226600 @default.
• W4380789068 cites W2276327097 @default.
• W4380789068 cites W2395611524 @default.
• W4380789068 cites W2412588858 @default.
• W4380789068 cites W2560023338 @default.
• W4380789068 cites W2749751926 @default.
• W4380789068 cites W2751181894 @default.
• W4380789068 cites W2752782242 @default.
• W4380789068 cites W2793116851 @default.
• W4380789068 cites W2802942478 @default.
• W4380789068 cites W2807956304 @default.
• W4380789068 cites W2884585870 @default.
• W4380789068 cites W2890730477 @default.
• W4380789068 cites W2904122576 @default.
• W4380789068 cites W2913128707 @default.
• W4380789068 cites W2954393156 @default.
• W4380789068 cites W2955058313 @default.
• W4380789068 cites W2963091558 @default.
• W4380789068 cites W2963323244 @default.
• W4380789068 cites W2963881378 @default.
• W4380789068 cites W2964309882 @default.
• W4380789068 cites W2995766874 @default.
• W4380789068 cites W2996290406 @default.
• W4380789068 cites W3016664505 @default.
• W4380789068 cites W3025800305 @default.
• W4380789068 cites W3033813277 @default.
• W4380789068 cites W3098881417 @default.
• W4380789068 cites W3103092912 @default.
• W4380789068 cites W3117652191 @default.
• W4380789068 cites W3118804988 @default.
• W4380789068 cites W3130455691 @default.
• W4380789068 cites W3138136606 @default.
• W4380789068 cites W3170697543 @default.
• W4380789068 cites W3175205795 @default.
• W4380789068 cites W3176945377 @default.
• W4380789068 cites W3189528951 @default.
• W4380789068 cites W3207493400 @default.
• W4380789068 cites W4200386693 @default.
• W4380789068 cites W4224882649 @default.
• W4380789068 cites W4281633835 @default.
• W4380789068 cites W4285301526 @default.
• W4380789068 cites W4290981008 @default.
• W4380789068 cites W4292553515 @default.
• W4380789068 cites W4303980720 @default.
• W4380789068 cites W4309455553 @default.
• W4380789068 cites W4312947755 @default.
• W4380789068 cites W4313196042 @default.
• W4380789068 cites W4324144346 @default.
• W4380789068 doi "https://doi.org/10.3390/rs15123121" @default.
• W4380789068 hasPublicationYear "2023" @default.
• W4380789068 type Work @default.
• W4380789068 citedByCount "0" @default.
• W4380789068 crossrefType "journal-article" @default.
• W4380789068 hasAuthorship W4380789068A5001865876 @default.
• W4380789068 hasAuthorship W4380789068A5017142254 @default.
• W4380789068 hasAuthorship W4380789068A5053687089 @default.
• W4380789068 hasAuthorship W4380789068A5060642323 @default.
• W4380789068 hasAuthorship W4380789068A5071995587 @default.
• W4380789068 hasAuthorship W4380789068A5083115565 @default.
• W4380789068 hasBestOaLocation W43807890681 @default.
• W4380789068 hasConcept C127313418 @default.
• W4380789068 hasConcept C153180895 @default.
• W4380789068 hasConcept C154945302 @default.
• W4380789068 hasConcept C41008148 @default.
• W4380789068 hasConcept C62649853 @default.
• W4380789068 hasConcept C81363708 @default.
• W4380789068 hasConcept C89600930 @default.
• W4380789068 hasConceptScore W4380789068C127313418 @default.
• W4380789068 hasConceptScore W4380789068C153180895 @default.
• W4380789068 hasConceptScore W4380789068C154945302 @default.
• W4380789068 hasConceptScore W4380789068C41008148 @default.
• W4380789068 hasConceptScore W4380789068C62649853 @default.
• W4380789068 hasConceptScore W4380789068C81363708 @default.
• W4380789068 hasConceptScore W4380789068C89600930 @default.
• W4380789068 hasIssue "12" @default.
• W4380789068 hasLocation W43807890681 @default.
• W4380789068 hasOpenAccess W4380789068 @default.
• W4380789068 hasPrimaryLocation W43807890681 @default.
• W4380789068 hasRelatedWork W2521062615 @default.
• W4380789068 hasRelatedWork W2735477435 @default.
• W4380789068 hasRelatedWork W2767651786 @default.
• W4380789068 hasRelatedWork W2912288872 @default.
• W4380789068 hasRelatedWork W3016958897 @default.
• W4380789068 hasRelatedWork W3045739591 @default.

• next