FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2802076210> ?p ?o ?g. }

• W2802076210 abstract "Semantic segmentation in high resolution remote sensing images is a fundamental and challenging task. Convolutional neural networks (CNNs), such as fully convolutional network (FCN) and SegNet, have shown outstanding performance in many segmentation tasks. One key pillar of these successes is mining useful information from features in convolutional layers for producing high resolution segmentation maps. For example, FCN nonlinearly combines high-level features extracted from last convolutional layers; whereas SegNet utilizes a deconvolutional network which takes as input only coarse, high-level feature maps of the last convolutional layer. However, how to better fuse multi-level convolutional feature maps for semantic segmentation of remote sensing images is underexplored. In this work, we propose a novel bidirectional network called recurrent network in fully convolutional network (RiFCN), which is end-to-end trainable. It has a forward stream and a backward stream. The former is a classification CNN architecture for feature extraction, which takes an input image and produces multi-level convolutional feature maps from shallow to deep; while in the later, to achieve accurate boundary inference and semantic segmentation, boundary-aware high resolution feature maps in shallower layers and high-level but low-resolution features are recursively embedded into the learning framework (from deep to shallow) to generate a fused feature representation that draws a holistic picture of not only high-level semantic information but also low-level fine-grained details. Experimental results on two widely-used high resolution remote sensing data sets for semantic segmentation tasks, ISPRS Potsdam and Inria Aerial Image Labeling Data Set, demonstrate competitive performance obtained by the proposed methodology compared to other studied approaches." @default.
• W2802076210 created "2018-05-17" @default.
• W2802076210 creator A5024379450 @default.
• W2802076210 creator A5068384981 @default.
• W2802076210 date "2018-05-05" @default.
• W2802076210 modified "2023-10-18" @default.
• W2802076210 title "RiFCN: Recurrent Network in Fully Convolutional Network for Semantic Segmentation of High Resolution Remote Sensing Images" @default.
• W2802076210 cites W104184427 @default.
• W2802076210 cites W1533861849 @default.
• W2802076210 cites W1536680647 @default.
• W2802076210 cites W1594676769 @default.
• W2802076210 cites W1849277567 @default.
• W2802076210 cites W1901129140 @default.
• W2802076210 cites W1903029394 @default.
• W2802076210 cites W1915485278 @default.
• W2802076210 cites W1965766334 @default.
• W2802076210 cites W2102605133 @default.
• W2802076210 cites W2127199143 @default.
• W2802076210 cites W2145094598 @default.
• W2802076210 cites W2147800946 @default.
• W2802076210 cites W2163605009 @default.
• W2802076210 cites W2194775991 @default.
• W2802076210 cites W2295107390 @default.
• W2802076210 cites W2431738724 @default.
• W2802076210 cites W2469938794 @default.
• W2802076210 cites W2480078828 @default.
• W2802076210 cites W2527276685 @default.
• W2802076210 cites W2547812480 @default.
• W2802076210 cites W2560023338 @default.
• W2802076210 cites W2563705555 @default.
• W2802076210 cites W2606788270 @default.
• W2802076210 cites W2612149202 @default.
• W2802076210 cites W2613718673 @default.
• W2802076210 cites W2624909539 @default.
• W2802076210 cites W2737391801 @default.
• W2802076210 cites W2757208835 @default.
• W2802076210 cites W2789688775 @default.
• W2802076210 cites W2901463460 @default.
• W2802076210 cites W2963150697 @default.
• W2802076210 cites W2963659230 @default.
• W2802076210 cites W2963881378 @default.
• W2802076210 cites W2963995737 @default.
• W2802076210 cites W2964121744 @default.
• W2802076210 cites W3101640299 @default.
• W2802076210 cites W3102850314 @default.
• W2802076210 cites W3104839310 @default.
• W2802076210 cites W3105127913 @default.
• W2802076210 doi "https://doi.org/10.48550/arxiv.1805.02091" @default.
• W2802076210 hasPublicationYear "2018" @default.
• W2802076210 type Work @default.
• W2802076210 sameAs 2802076210 @default.
• W2802076210 citedByCount "8" @default.
• W2802076210 countsByYear W28020762102019 @default.
• W2802076210 countsByYear W28020762102020 @default.
• W2802076210 countsByYear W28020762102021 @default.
• W2802076210 countsByYear W28020762102023 @default.
• W2802076210 crossrefType "posted-content" @default.
• W2802076210 hasAuthorship W2802076210A5024379450 @default.
• W2802076210 hasAuthorship W2802076210A5068384981 @default.
• W2802076210 hasBestOaLocation W28020762101 @default.
• W2802076210 hasConcept C108583219 @default.
• W2802076210 hasConcept C124504099 @default.
• W2802076210 hasConcept C138885662 @default.
• W2802076210 hasConcept C153180895 @default.
• W2802076210 hasConcept C154945302 @default.
• W2802076210 hasConcept C2776214188 @default.
• W2802076210 hasConcept C2776401178 @default.
• W2802076210 hasConcept C31972630 @default.
• W2802076210 hasConcept C41008148 @default.
• W2802076210 hasConcept C41895202 @default.
• W2802076210 hasConcept C52622490 @default.
• W2802076210 hasConcept C81363708 @default.
• W2802076210 hasConcept C89600930 @default.
• W2802076210 hasConceptScore W2802076210C108583219 @default.
• W2802076210 hasConceptScore W2802076210C124504099 @default.
• W2802076210 hasConceptScore W2802076210C138885662 @default.
• W2802076210 hasConceptScore W2802076210C153180895 @default.
• W2802076210 hasConceptScore W2802076210C154945302 @default.
• W2802076210 hasConceptScore W2802076210C2776214188 @default.
• W2802076210 hasConceptScore W2802076210C2776401178 @default.
• W2802076210 hasConceptScore W2802076210C31972630 @default.
• W2802076210 hasConceptScore W2802076210C41008148 @default.
• W2802076210 hasConceptScore W2802076210C41895202 @default.
• W2802076210 hasConceptScore W2802076210C52622490 @default.
• W2802076210 hasConceptScore W2802076210C81363708 @default.
• W2802076210 hasConceptScore W2802076210C89600930 @default.
• W2802076210 hasLocation W28020762101 @default.
• W2802076210 hasOpenAccess W2802076210 @default.
• W2802076210 hasPrimaryLocation W28020762101 @default.
• W2802076210 hasRelatedWork W2279398222 @default.
• W2802076210 hasRelatedWork W2406522397 @default.
• W2802076210 hasRelatedWork W2732542196 @default.
• W2802076210 hasRelatedWork W2773120646 @default.
• W2802076210 hasRelatedWork W2795329967 @default.
• W2802076210 hasRelatedWork W3102253946 @default.
• W2802076210 hasRelatedWork W3144574764 @default.
• W2802076210 hasRelatedWork W4226289457 @default.
• W2802076210 hasRelatedWork W4293211451 @default.
• W2802076210 hasRelatedWork W4299822940 @default.
• W2802076210 isParatext "false" @default.

• next