FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367325736> ?p ?o ?g. }

• W4367325736 endingPage "2293" @default.
• W4367325736 startingPage "2293" @default.
• W4367325736 abstract "Semantic segmentation of remote-sensing (RS) images is one of the most fundamental tasks in the understanding of a remote-sensing scene. However, high-resolution RS images contain plentiful detailed information about ground objects, which scatter everywhere spatially and have variable sizes, styles, and visual appearances. Due to the high similarity between classes and diversity within classes, it is challenging to obtain satisfactory and accurate semantic segmentation results. This paper proposes a Dynamic High-Resolution Network (DyHRNet) to solve this problem. Our proposed network takes HRNet as a super-architecture, aiming to leverage the important connections and channels by further investigating the parallel streams at different resolution representations of the original HRNet. The learning task is conducted under the framework of a neural architecture search (NAS) and channel-wise attention module. Specifically, the Accelerated Proximal Gradient (APG) algorithm is introduced to iteratively solve the sparse regularization subproblem from the perspective of neural architecture search. In this way, valuable connections are selected for cross-resolution feature fusion. In addition, a channel-wise attention module is designed to weight the channel contributions for feature aggregation. Finally, DyHRNet fully realizes the dynamic advantages of data adaptability by combining the APG algorithm and channel-wise attention module simultaneously. Compared with nine classical or state-of-the-art models (FCN, UNet, PSPNet, DeepLabV3+, OCRNet, SETR, SegFormer, HRNet+FCN, and HRNet+OCR), DyHRNet has shown high performance on three public challenging RS image datasets (Vaihingen, Potsdam, and LoveDA). Furthermore, the visual segmentation results, the learned structures, the iteration process analysis, and the ablation study all demonstrate the effectiveness of our proposed model." @default.
• W4367325736 created "2023-04-29" @default.
• W4367325736 creator A5011561150 @default.
• W4367325736 creator A5024842018 @default.
• W4367325736 creator A5040072659 @default.
• W4367325736 creator A5040673285 @default.
• W4367325736 creator A5051125527 @default.
• W4367325736 date "2023-04-26" @default.
• W4367325736 modified "2023-10-01" @default.
• W4367325736 title "Dynamic High-Resolution Network for Semantic Segmentation in Remote-Sensing Images" @default.
• W4367325736 cites W1901129140 @default.
• W4367325736 cites W2117539524 @default.
• W4367325736 cites W2194775991 @default.
• W4367325736 cites W2560023338 @default.
• W4367325736 cites W2623490820 @default.
• W4367325736 cites W2731489139 @default.
• W4367325736 cites W2758000438 @default.
• W4367325736 cites W2778539913 @default.
• W4367325736 cites W2782475589 @default.
• W4367325736 cites W2794948653 @default.
• W4367325736 cites W2897295818 @default.
• W4367325736 cites W2902540630 @default.
• W4367325736 cites W2916798096 @default.
• W4367325736 cites W2922509574 @default.
• W4367325736 cites W2927980542 @default.
• W4367325736 cites W2963136578 @default.
• W4367325736 cites W2964309882 @default.
• W4367325736 cites W2964444661 @default.
• W4367325736 cites W2969911358 @default.
• W4367325736 cites W2996102538 @default.
• W4367325736 cites W3007268491 @default.
• W4367325736 cites W3008156909 @default.
• W4367325736 cites W3014641072 @default.
• W4367325736 cites W3034399482 @default.
• W4367325736 cites W3082002974 @default.
• W4367325736 cites W3082366738 @default.
• W4367325736 cites W3085633928 @default.
• W4367325736 cites W3088431851 @default.
• W4367325736 cites W3103092912 @default.
• W4367325736 cites W3110908156 @default.
• W4367325736 cites W3117812033 @default.
• W4367325736 cites W3129544296 @default.
• W4367325736 cites W3163636357 @default.
• W4367325736 cites W3170841864 @default.
• W4367325736 cites W3171398643 @default.
• W4367325736 cites W3180150746 @default.
• W4367325736 cites W3202223246 @default.
• W4367325736 cites W4200547174 @default.
• W4367325736 cites W4244393449 @default.
• W4367325736 cites W4285601475 @default.
• W4367325736 cites W4291014824 @default.
• W4367325736 cites W4312832377 @default.
• W4367325736 cites W4319300529 @default.
• W4367325736 doi "https://doi.org/10.3390/rs15092293" @default.
• W4367325736 hasPublicationYear "2023" @default.
• W4367325736 type Work @default.
• W4367325736 citedByCount "0" @default.
• W4367325736 crossrefType "journal-article" @default.
• W4367325736 hasAuthorship W4367325736A5011561150 @default.
• W4367325736 hasAuthorship W4367325736A5024842018 @default.
• W4367325736 hasAuthorship W4367325736A5040072659 @default.
• W4367325736 hasAuthorship W4367325736A5040673285 @default.
• W4367325736 hasAuthorship W4367325736A5051125527 @default.
• W4367325736 hasBestOaLocation W43673257361 @default.
• W4367325736 hasConcept C111919701 @default.
• W4367325736 hasConcept C127162648 @default.
• W4367325736 hasConcept C127313418 @default.
• W4367325736 hasConcept C138885662 @default.
• W4367325736 hasConcept C153083717 @default.
• W4367325736 hasConcept C153180895 @default.
• W4367325736 hasConcept C154945302 @default.
• W4367325736 hasConcept C2776135515 @default.
• W4367325736 hasConcept C2776401178 @default.
• W4367325736 hasConcept C3020199158 @default.
• W4367325736 hasConcept C31258907 @default.
• W4367325736 hasConcept C31972630 @default.
• W4367325736 hasConcept C41008148 @default.
• W4367325736 hasConcept C41895202 @default.
• W4367325736 hasConcept C62649853 @default.
• W4367325736 hasConcept C89600930 @default.
• W4367325736 hasConcept C98045186 @default.
• W4367325736 hasConceptScore W4367325736C111919701 @default.
• W4367325736 hasConceptScore W4367325736C127162648 @default.
• W4367325736 hasConceptScore W4367325736C127313418 @default.
• W4367325736 hasConceptScore W4367325736C138885662 @default.
• W4367325736 hasConceptScore W4367325736C153083717 @default.
• W4367325736 hasConceptScore W4367325736C153180895 @default.
• W4367325736 hasConceptScore W4367325736C154945302 @default.
• W4367325736 hasConceptScore W4367325736C2776135515 @default.
• W4367325736 hasConceptScore W4367325736C2776401178 @default.
• W4367325736 hasConceptScore W4367325736C3020199158 @default.
• W4367325736 hasConceptScore W4367325736C31258907 @default.
• W4367325736 hasConceptScore W4367325736C31972630 @default.
• W4367325736 hasConceptScore W4367325736C41008148 @default.
• W4367325736 hasConceptScore W4367325736C41895202 @default.
• W4367325736 hasConceptScore W4367325736C62649853 @default.
• W4367325736 hasConceptScore W4367325736C89600930 @default.
• W4367325736 hasConceptScore W4367325736C98045186 @default.

• next