FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312437942> ?p ?o ?g. }

• W4312437942 endingPage "1082" @default.
• W4312437942 startingPage "1058" @default.
• W4312437942 abstract "Limited by GPU memory, high-resolution image segmentation is a highly challenging task. To improve the accuracy of high-resolution segmentation, High-Resolution Refine Net (HRRNet) is proposed. The network is divided into a rough segmentation module and a refinement module. The former improves DeepLabV3+ by adding the shallow features of 1/2 original image size and the corresponding skip connection to obtain better rough segmentation results, the output of which is used as the input of the latter. In the refinement module, first, the global context information of the input image is obtained by a global process. Second, the high-resolution image is divided into patches, and each patch is processed separately to obtain local details in a local process. In both processes, multiple refine units (RU) are cascaded for refinement processing, and two cascaded residual convolutional units (RCU) are added to the different output paths of RU to improve the mIoU and the convergence speed of the network. Finally, according to the context information of the global process, the refined patches are pieced to obtain the refined segmentation result of the whole high-resolution image. In addition, the regional non-maximum suppression is introduced to improve the Sobel edge detection, and the Pascal VOC 2012 dataset is enhanced, which improves the segmentation accuracy and robust performance of the network. Compared with the state-of-the-art semantic segmentation models, the experimental results show that our model achieves the best performance in high-resolution image segmentation." @default.
• W4312437942 created "2023-01-04" @default.
• W4312437942 creator A5055761370 @default.
• W4312437942 creator A5080546052 @default.
• W4312437942 date "2022-01-01" @default.
• W4312437942 modified "2023-10-14" @default.
• W4312437942 title "A robust and high-precision edge segmentation and refinement method for high-resolution images" @default.
• W4312437942 cites W1901129140 @default.
• W4312437942 cites W2039313011 @default.
• W4312437942 cites W2194775991 @default.
• W4312437942 cites W2294182682 @default.
• W4312437942 cites W2395611524 @default.
• W4312437942 cites W2412782625 @default.
• W4312437942 cites W2517954747 @default.
• W4312437942 cites W2560023338 @default.
• W4312437942 cites W2563705555 @default.
• W4312437942 cites W2744480060 @default.
• W4312437942 cites W2749689071 @default.
• W4312437942 cites W2804199516 @default.
• W4312437942 cites W2884585870 @default.
• W4312437942 cites W2886934227 @default.
• W4312437942 cites W2889628364 @default.
• W4312437942 cites W2946824094 @default.
• W4312437942 cites W2955058313 @default.
• W4312437942 cites W2963091558 @default.
• W4312437942 cites W2963163009 @default.
• W4312437942 cites W2963599420 @default.
• W4312437942 cites W2963881378 @default.
• W4312437942 cites W2964309882 @default.
• W4312437942 cites W2965729941 @default.
• W4312437942 cites W2981689412 @default.
• W4312437942 cites W2982083293 @default.
• W4312437942 cites W3016150174 @default.
• W4312437942 cites W3034427230 @default.
• W4312437942 cites W3034438741 @default.
• W4312437942 cites W3035028692 @default.
• W4312437942 cites W3102404821 @default.
• W4312437942 cites W3166016280 @default.
• W4312437942 cites W3170841864 @default.
• W4312437942 cites W3172798612 @default.
• W4312437942 cites W3186351311 @default.
• W4312437942 cites W3192525833 @default.
• W4312437942 cites W3196904463 @default.
• W4312437942 cites W3197006556 @default.
• W4312437942 cites W3211490618 @default.
• W4312437942 cites W4210571542 @default.
• W4312437942 cites W4214520160 @default.
• W4312437942 cites W4214893857 @default.
• W4312437942 cites W4239147634 @default.
• W4312437942 doi "https://doi.org/10.3934/mbe.2023049" @default.
• W4312437942 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36650802" @default.
• W4312437942 hasPublicationYear "2022" @default.
• W4312437942 type Work @default.
• W4312437942 citedByCount "0" @default.
• W4312437942 crossrefType "journal-article" @default.
• W4312437942 hasAuthorship W4312437942A5055761370 @default.
• W4312437942 hasAuthorship W4312437942A5080546052 @default.
• W4312437942 hasBestOaLocation W43124379421 @default.
• W4312437942 hasConcept C11413529 @default.
• W4312437942 hasConcept C124504099 @default.
• W4312437942 hasConcept C151730666 @default.
• W4312437942 hasConcept C153180895 @default.
• W4312437942 hasConcept C154945302 @default.
• W4312437942 hasConcept C155512373 @default.
• W4312437942 hasConcept C199360897 @default.
• W4312437942 hasConcept C205372480 @default.
• W4312437942 hasConcept C25694479 @default.
• W4312437942 hasConcept C2779343474 @default.
• W4312437942 hasConcept C31972630 @default.
• W4312437942 hasConcept C41008148 @default.
• W4312437942 hasConcept C65885262 @default.
• W4312437942 hasConcept C75608658 @default.
• W4312437942 hasConcept C86803240 @default.
• W4312437942 hasConcept C89600930 @default.
• W4312437942 hasConceptScore W4312437942C11413529 @default.
• W4312437942 hasConceptScore W4312437942C124504099 @default.
• W4312437942 hasConceptScore W4312437942C151730666 @default.
• W4312437942 hasConceptScore W4312437942C153180895 @default.
• W4312437942 hasConceptScore W4312437942C154945302 @default.
• W4312437942 hasConceptScore W4312437942C155512373 @default.
• W4312437942 hasConceptScore W4312437942C199360897 @default.
• W4312437942 hasConceptScore W4312437942C205372480 @default.
• W4312437942 hasConceptScore W4312437942C25694479 @default.
• W4312437942 hasConceptScore W4312437942C2779343474 @default.
• W4312437942 hasConceptScore W4312437942C31972630 @default.
• W4312437942 hasConceptScore W4312437942C41008148 @default.
• W4312437942 hasConceptScore W4312437942C65885262 @default.
• W4312437942 hasConceptScore W4312437942C75608658 @default.
• W4312437942 hasConceptScore W4312437942C86803240 @default.
• W4312437942 hasConceptScore W4312437942C89600930 @default.
• W4312437942 hasIssue "1" @default.
• W4312437942 hasLocation W43124379421 @default.
• W4312437942 hasLocation W43124379422 @default.
• W4312437942 hasOpenAccess W4312437942 @default.
• W4312437942 hasPrimaryLocation W43124379421 @default.
• W4312437942 hasRelatedWork W134976887 @default.
• W4312437942 hasRelatedWork W1669643531 @default.
• W4312437942 hasRelatedWork W1982826852 @default.

• next