FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376140744> ?p ?o ?g. }

• W4376140744 abstract "Distress segmentation assigns each pixel of a pavement image to one distress class or background, which provides a simplified representation for distress detection and measurement. Even though remarkably benefiting from deep learning, distress segmentation still faces the problems of poor calibration and multimodel fusion. This study has proposed a deep neural network by combining the Dempster–Shafer theory (DST) and a transformer network for pavement distress segmentation. The network, called the evidential segmentation transformer, uses its transformer backbone to obtain pixel-wise features from input images. The features are then converted into pixel-wise mass functions by a DST-based evidence layer. The pixel-wise masses are utilized for performing distress segmentation based on the pignistic criterion. The proposed network is iteratively trained by a new learning strategy, which represents uncertain information of ambiguous pixels by mass functions. In addition, an evidential fusion strategy is proposed to fuse heterogeneous transformers with different distress classes. Experiments using three public data sets (Pavementscape, Crack500, and CrackDataset) show that the proposed networks achieve state-of-the-art accuracy and calibration on distress segmentation, which allows for measuring the distress shapes more accurately and stably. The proposed fusion strategy combines heterogeneous transformers while remaining a performance not less than those of the individual networks on their respective data sets. Thus, the fusion strategy makes it possible to use the existing networks to build a more general and accurate one for distress segmentation." @default.
• W4376140744 created "2023-05-12" @default.
• W4376140744 creator A5001838653 @default.
• W4376140744 creator A5028952393 @default.
• W4376140744 creator A5055024212 @default.
• W4376140744 creator A5085672523 @default.
• W4376140744 date "2023-05-10" @default.
• W4376140744 modified "2023-10-14" @default.
• W4376140744 title "Evidential transformer for pavement distress segmentation" @default.
• W4376140744 cites W1578800471 @default.
• W4376140744 cites W1861492603 @default.
• W4376140744 cites W1901129140 @default.
• W4376140744 cites W1903029394 @default.
• W4376140744 cites W2037227137 @default.
• W4376140744 cites W2158572399 @default.
• W4376140744 cites W2176450933 @default.
• W4376140744 cites W2340897893 @default.
• W4376140744 cites W2406470551 @default.
• W4376140744 cites W2412782625 @default.
• W4376140744 cites W2596678650 @default.
• W4376140744 cites W2736832651 @default.
• W4376140744 cites W2748643398 @default.
• W4376140744 cites W2765854388 @default.
• W4376140744 cites W2800691917 @default.
• W4376140744 cites W2801492038 @default.
• W4376140744 cites W2810441858 @default.
• W4376140744 cites W2886369963 @default.
• W4376140744 cites W2887693548 @default.
• W4376140744 cites W2887872047 @default.
• W4376140744 cites W2903583898 @default.
• W4376140744 cites W2921440296 @default.
• W4376140744 cites W2964308596 @default.
• W4376140744 cites W2965768175 @default.
• W4376140744 cites W2966126335 @default.
• W4376140744 cites W2981689412 @default.
• W4376140744 cites W2993973806 @default.
• W4376140744 cites W2996251405 @default.
• W4376140744 cites W3000491742 @default.
• W4376140744 cites W3001104520 @default.
• W4376140744 cites W3011200270 @default.
• W4376140744 cites W3012971642 @default.
• W4376140744 cites W3016719260 @default.
• W4376140744 cites W3025800305 @default.
• W4376140744 cites W3036991312 @default.
• W4376140744 cites W3099564553 @default.
• W4376140744 cites W3110387610 @default.
• W4376140744 cites W3146464195 @default.
• W4376140744 cites W3155812415 @default.
• W4376140744 cites W3158395436 @default.
• W4376140744 cites W3171093259 @default.
• W4376140744 cites W3203911595 @default.
• W4376140744 cites W3210043680 @default.
• W4376140744 cites W4200042261 @default.
• W4376140744 cites W4214893857 @default.
• W4376140744 cites W4220780913 @default.
• W4376140744 cites W4224244676 @default.
• W4376140744 cites W4225400017 @default.
• W4376140744 cites W4293241557 @default.
• W4376140744 cites W4293457170 @default.
• W4376140744 cites W4301347335 @default.
• W4376140744 doi "https://doi.org/10.1111/mice.13018" @default.
• W4376140744 hasPublicationYear "2023" @default.
• W4376140744 type Work @default.
• W4376140744 citedByCount "0" @default.
• W4376140744 crossrefType "journal-article" @default.
• W4376140744 hasAuthorship W4376140744A5001838653 @default.
• W4376140744 hasAuthorship W4376140744A5028952393 @default.
• W4376140744 hasAuthorship W4376140744A5055024212 @default.
• W4376140744 hasAuthorship W4376140744A5085672523 @default.
• W4376140744 hasConcept C119599485 @default.
• W4376140744 hasConcept C124504099 @default.
• W4376140744 hasConcept C127413603 @default.
• W4376140744 hasConcept C139265228 @default.
• W4376140744 hasConcept C153180895 @default.
• W4376140744 hasConcept C154945302 @default.
• W4376140744 hasConcept C15744967 @default.
• W4376140744 hasConcept C160633673 @default.
• W4376140744 hasConcept C165801399 @default.
• W4376140744 hasConcept C31972630 @default.
• W4376140744 hasConcept C41008148 @default.
• W4376140744 hasConcept C50644808 @default.
• W4376140744 hasConcept C542102704 @default.
• W4376140744 hasConcept C66322947 @default.
• W4376140744 hasConcept C89600930 @default.
• W4376140744 hasConceptScore W4376140744C119599485 @default.
• W4376140744 hasConceptScore W4376140744C124504099 @default.
• W4376140744 hasConceptScore W4376140744C127413603 @default.
• W4376140744 hasConceptScore W4376140744C139265228 @default.
• W4376140744 hasConceptScore W4376140744C153180895 @default.
• W4376140744 hasConceptScore W4376140744C154945302 @default.
• W4376140744 hasConceptScore W4376140744C15744967 @default.
• W4376140744 hasConceptScore W4376140744C160633673 @default.
• W4376140744 hasConceptScore W4376140744C165801399 @default.
• W4376140744 hasConceptScore W4376140744C31972630 @default.
• W4376140744 hasConceptScore W4376140744C41008148 @default.
• W4376140744 hasConceptScore W4376140744C50644808 @default.
• W4376140744 hasConceptScore W4376140744C542102704 @default.
• W4376140744 hasConceptScore W4376140744C66322947 @default.
• W4376140744 hasConceptScore W4376140744C89600930 @default.
• W4376140744 hasLocation W43761407441 @default.

• next