FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3206254920> ?p ?o ?g. }

• W3206254920 endingPage "18" @default.
• W3206254920 startingPage "1" @default.
• W3206254920 abstract "Semantic segmentation in aerial imagery is still an important, yet challenging task due to the complex characteristics of remote-sensing data. The critical issues consist of: 1) extreme foreground–background imbalance; 2) large intra-class variance; and 3) arbitrary-oriented, dense, and small objects. The above challenges make it unlikely to model the effective global interdependencies of semantic heterogeneous regions. Besides, general semantic segmentation methods suffer from feature ambiguity due to the joint feature learning paradigm, leading to inferior detail information. In this article, we propose an improved semantic segmentation framework to tackle these problems via graph reasoning (GR) and disentangled learning. On the one hand, a simple, yet effective GR unit is introduced to implement coordinate-interaction space mapping and perform relation reasoning over the graph. It can be deployed on the feature pyramid network (FPN) to exploit cross-stage multi-scale information. On the other hand, we propose a so- called disentangled learning paradigm to explicitly model the foreground and boundary objects, instantiated as foreground prior estimation (FPE) and boundary alignment (BA). The indication of the intermediate feature can be effectively emphasized to enhance the discriminative abilities of the network. Extensive experiments over iSAID, ISPRS Vaihingen, and the general Cityscapes datasets demonstrate the effectiveness and efficiency of the proposed framework over other state-of-the-art semantic segmentation methods." @default.
• W3206254920 created "2021-10-25" @default.
• W3206254920 creator A5002059265 @default.
• W3206254920 creator A5002110023 @default.
• W3206254920 creator A5005905514 @default.
• W3206254920 creator A5016825672 @default.
• W3206254920 creator A5048813928 @default.
• W3206254920 creator A5055032051 @default.
• W3206254920 date "2022-01-01" @default.
• W3206254920 modified "2023-09-26" @default.
• W3206254920 title "Improving Semantic Segmentation in Aerial Imagery via Graph Reasoning and Disentangled Learning" @default.
• W3206254920 cites W1901129140 @default.
• W3206254920 cites W1903029394 @default.
• W3206254920 cites W2034906331 @default.
• W3206254920 cites W2104657103 @default.
• W3206254920 cites W2117539524 @default.
• W3206254920 cites W2163922914 @default.
• W3206254920 cites W2194775991 @default.
• W3206254920 cites W2340897893 @default.
• W3206254920 cites W2412782625 @default.
• W3206254920 cites W2560023338 @default.
• W3206254920 cites W2560474170 @default.
• W3206254920 cites W2563705555 @default.
• W3206254920 cites W2601564443 @default.
• W3206254920 cites W2752782242 @default.
• W3206254920 cites W2773004715 @default.
• W3206254920 cites W2774320778 @default.
• W3206254920 cites W2778539913 @default.
• W3206254920 cites W2793461576 @default.
• W3206254920 cites W2799213142 @default.
• W3206254920 cites W2806331055 @default.
• W3206254920 cites W2883502031 @default.
• W3206254920 cites W2884585870 @default.
• W3206254920 cites W2884822772 @default.
• W3206254920 cites W2895340641 @default.
• W3206254920 cites W2901442382 @default.
• W3206254920 cites W2948519073 @default.
• W3206254920 cites W2955058313 @default.
• W3206254920 cites W2955186028 @default.
• W3206254920 cites W2962914239 @default.
• W3206254920 cites W2963073398 @default.
• W3206254920 cites W2963091558 @default.
• W3206254920 cites W2963236837 @default.
• W3206254920 cites W2963319519 @default.
• W3206254920 cites W2963351448 @default.
• W3206254920 cites W2963659230 @default.
• W3206254920 cites W2963727650 @default.
• W3206254920 cites W2963881378 @default.
• W3206254920 cites W2963890956 @default.
• W3206254920 cites W2963995737 @default.
• W3206254920 cites W2964184826 @default.
• W3206254920 cites W2981539886 @default.
• W3206254920 cites W2981689412 @default.
• W3206254920 cites W2981899103 @default.
• W3206254920 cites W2982220924 @default.
• W3206254920 cites W2990392801 @default.
• W3206254920 cites W2991471181 @default.
• W3206254920 cites W2993235622 @default.
• W3206254920 cites W3014641072 @default.
• W3206254920 cites W3018169007 @default.
• W3206254920 cites W3034345703 @default.
• W3206254920 cites W3034427230 @default.
• W3206254920 cites W3034951775 @default.
• W3206254920 cites W3035339581 @default.
• W3206254920 cites W3035526186 @default.
• W3206254920 cites W3047053653 @default.
• W3206254920 cites W3047922927 @default.
• W3206254920 cites W3083065220 @default.
• W3206254920 cites W3096653763 @default.
• W3206254920 cites W3107113572 @default.
• W3206254920 cites W3107634219 @default.
• W3206254920 cites W3108186749 @default.
• W3206254920 cites W3109196706 @default.
• W3206254920 cites W3110440461 @default.
• W3206254920 cites W3133630855 @default.
• W3206254920 cites W3164443777 @default.
• W3206254920 cites W3168495321 @default.
• W3206254920 cites W3170841864 @default.
• W3206254920 cites W764651262 @default.
• W3206254920 doi "https://doi.org/10.1109/tgrs.2021.3121471" @default.
• W3206254920 hasPublicationYear "2022" @default.
• W3206254920 type Work @default.
• W3206254920 sameAs 3206254920 @default.
• W3206254920 citedByCount "5" @default.
• W3206254920 countsByYear W32062549202022 @default.
• W3206254920 countsByYear W32062549202023 @default.
• W3206254920 crossrefType "journal-article" @default.
• W3206254920 hasAuthorship W3206254920A5002059265 @default.
• W3206254920 hasAuthorship W3206254920A5002110023 @default.
• W3206254920 hasAuthorship W3206254920A5005905514 @default.
• W3206254920 hasAuthorship W3206254920A5016825672 @default.
• W3206254920 hasAuthorship W3206254920A5048813928 @default.
• W3206254920 hasAuthorship W3206254920A5055032051 @default.
• W3206254920 hasConcept C119857082 @default.
• W3206254920 hasConcept C132525143 @default.
• W3206254920 hasConcept C138885662 @default.
• W3206254920 hasConcept C153180895 @default.
• W3206254920 hasConcept C154945302 @default.

• next