FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313555728> ?p ?o ?g. }

• W4313555728 endingPage "14" @default.
• W4313555728 startingPage "1" @default.
• W4313555728 abstract "Semantic segmentation of Very High Resolution (VHR) remote sensing images is a fundamental task for many applications. However, large variations in the scales of objects in those VHR images pose a challenge for performing accurate semantic segmentation. Existing semantic segmentation networks are able to analyse an input image at up to four resizing scales, but this may be insufficient given the diversity of object scales. Therefore, Multi Scale (MS) test-time data augmentation is often used in practice to obtain more accurate segmentation results, which makes equal use of the segmentation results obtained at the different resizing scales. However, it was found in this study that different classes of objects had their preferred resizing scale for more accurate semantic segmentation. Based on this behaviour, a Stacking-Based Semantic Segmentation (SBSS) framework is proposed to improve the segmentation results by learning this behaviour, which contains a learnable Error Correction Module (ECM) for segmentation result fusion and an Error Correction Scheme (ECS) for computational complexity control. Two ECS, i.e., ECS-MS and ECS-SS, are proposed and investigated in this study. The Floating-point operations (Flops) required for ECS-MS and ECS-SS are similar to the commonly used MS test and the Single-Scale (SS) test, respectively. Extensive experiments on four datasets (i.e., Cityscapes, UAVid, LoveDA and Potsdam) show that SBSS is an effective and flexible framework. It achieved higher accuracy than MS when using ECS-MS, and similar accuracy as SS with a quarter of the memory footprint when using ECS-SS." @default.
• W4313555728 created "2023-01-06" @default.
• W4313555728 creator A5028436114 @default.
• W4313555728 creator A5040553070 @default.
• W4313555728 creator A5059040724 @default.
• W4313555728 date "2023-01-01" @default.
• W4313555728 modified "2023-09-30" @default.
• W4313555728 title "SBSS: Stacking-Based Semantic Segmentation Framework for Very High-Resolution Remote Sensing Image" @default.
• W4313555728 cites W1963860205 @default.
• W4313555728 cites W1990322717 @default.
• W4313555728 cites W2109255472 @default.
• W4313555728 cites W2194775991 @default.
• W4313555728 cites W2340897893 @default.
• W4313555728 cites W2412782625 @default.
• W4313555728 cites W2531409750 @default.
• W4313555728 cites W2560023338 @default.
• W4313555728 cites W2810004461 @default.
• W4313555728 cites W28412257 @default.
• W4313555728 cites W2884822772 @default.
• W4313555728 cites W2886934227 @default.
• W4313555728 cites W2911964244 @default.
• W4313555728 cites W2963163009 @default.
• W4313555728 cites W2963659230 @default.
• W4313555728 cites W2964309882 @default.
• W4313555728 cites W2982220924 @default.
• W4313555728 cites W3003394660 @default.
• W4313555728 cites W3007363984 @default.
• W4313555728 cites W3014641072 @default.
• W4313555728 cites W3028752951 @default.
• W4313555728 cites W3093142463 @default.
• W4313555728 cites W3107634219 @default.
• W4313555728 cites W3109301572 @default.
• W4313555728 cites W3115007495 @default.
• W4313555728 cites W3128055887 @default.
• W4313555728 cites W3138516171 @default.
• W4313555728 cites W3140053374 @default.
• W4313555728 cites W3194376449 @default.
• W4313555728 cites W3198533054 @default.
• W4313555728 cites W3200075728 @default.
• W4313555728 cites W3215235459 @default.
• W4313555728 cites W4212883601 @default.
• W4313555728 cites W4220840476 @default.
• W4313555728 cites W4244313837 @default.
• W4313555728 doi "https://doi.org/10.1109/tgrs.2023.3234549" @default.
• W4313555728 hasPublicationYear "2023" @default.
• W4313555728 type Work @default.
• W4313555728 citedByCount "1" @default.
• W4313555728 countsByYear W43135557282023 @default.
• W4313555728 crossrefType "journal-article" @default.
• W4313555728 hasAuthorship W4313555728A5028436114 @default.
• W4313555728 hasAuthorship W4313555728A5040553070 @default.
• W4313555728 hasAuthorship W4313555728A5059040724 @default.
• W4313555728 hasBestOaLocation W43135557282 @default.
• W4313555728 hasConcept C121332964 @default.
• W4313555728 hasConcept C124504099 @default.
• W4313555728 hasConcept C153180895 @default.
• W4313555728 hasConcept C154945302 @default.
• W4313555728 hasConcept C2778755073 @default.
• W4313555728 hasConcept C31972630 @default.
• W4313555728 hasConcept C41008148 @default.
• W4313555728 hasConcept C62520636 @default.
• W4313555728 hasConcept C65885262 @default.
• W4313555728 hasConcept C89600930 @default.
• W4313555728 hasConceptScore W4313555728C121332964 @default.
• W4313555728 hasConceptScore W4313555728C124504099 @default.
• W4313555728 hasConceptScore W4313555728C153180895 @default.
• W4313555728 hasConceptScore W4313555728C154945302 @default.
• W4313555728 hasConceptScore W4313555728C2778755073 @default.
• W4313555728 hasConceptScore W4313555728C31972630 @default.
• W4313555728 hasConceptScore W4313555728C41008148 @default.
• W4313555728 hasConceptScore W4313555728C62520636 @default.
• W4313555728 hasConceptScore W4313555728C65885262 @default.
• W4313555728 hasConceptScore W4313555728C89600930 @default.
• W4313555728 hasLocation W43135557281 @default.
• W4313555728 hasLocation W43135557282 @default.
• W4313555728 hasLocation W43135557283 @default.
• W4313555728 hasOpenAccess W4313555728 @default.
• W4313555728 hasPrimaryLocation W43135557281 @default.
• W4313555728 hasRelatedWork W134976887 @default.
• W4313555728 hasRelatedWork W1669643531 @default.
• W4313555728 hasRelatedWork W1982826852 @default.
• W4313555728 hasRelatedWork W2005437358 @default.
• W4313555728 hasRelatedWork W2110230079 @default.
• W4313555728 hasRelatedWork W2384989255 @default.
• W4313555728 hasRelatedWork W2517104666 @default.
• W4313555728 hasRelatedWork W2549936415 @default.
• W4313555728 hasRelatedWork W2566648451 @default.
• W4313555728 hasRelatedWork W1967061043 @default.
• W4313555728 hasVolume "61" @default.
• W4313555728 isParatext "false" @default.
• W4313555728 isRetracted "false" @default.
• W4313555728 workType "article" @default.