Matches in SemOpenAlex for { <https://semopenalex.org/work/W3114606989> ?p ?o ?g. }
- W3114606989 endingPage "2161" @default.
- W3114606989 startingPage "2148" @default.
- W3114606989 abstract "In recent years, despite the tremendous progresses of object detection, small object detection has always been a challenge in the field of remote sensing. The main reason is that small objects cover few features that are easily lost during down-sampling. In this article, we propose a cross-layer attention network aiming to obtain stronger features of small objects for better detection. Specifically, we designed an up-sampling and down-sampling feature pyramid to obtain richer context information by bidirectionally fusing deep and shallow features, as well as skipping connections. Moreover, a cross-layer attention module is designed to obtain the nonlocal association of small objects in each layer, and further strengthen its representation ability through cross-layer integration and balance. Extensive experiments on the publicly available datasets (DIOR dataset and NWPUVHR-10 dataset) and the self-assembled datasets (SDOTA dataset and SDD dataset) show the excellent performance of our method compared with other detectors. Moreover, our method achieved 74.3% mAP on the public DIOR dataset without any tricks." @default.
- W3114606989 created "2021-01-05" @default.
- W3114606989 creator A5023578647 @default.
- W3114606989 creator A5049747868 @default.
- W3114606989 creator A5050630882 @default.
- W3114606989 creator A5054791684 @default.
- W3114606989 creator A5054800338 @default.
- W3114606989 creator A5088717109 @default.
- W3114606989 date "2021-01-01" @default.
- W3114606989 modified "2023-10-16" @default.
- W3114606989 title "Cross-Layer Attention Network for Small Object Detection in Remote Sensing Imagery" @default.
- W3114606989 cites W2005368619 @default.
- W3114606989 cites W2017448754 @default.
- W3114606989 cites W2031489346 @default.
- W3114606989 cites W2194775991 @default.
- W3114606989 cites W2512351403 @default.
- W3114606989 cites W2565639579 @default.
- W3114606989 cites W2570343428 @default.
- W3114606989 cites W2752782242 @default.
- W3114606989 cites W2779335303 @default.
- W3114606989 cites W2788202095 @default.
- W3114606989 cites W2804436788 @default.
- W3114606989 cites W2808360995 @default.
- W3114606989 cites W2888527098 @default.
- W3114606989 cites W2931790542 @default.
- W3114606989 cites W2946802127 @default.
- W3114606989 cites W2962721361 @default.
- W3114606989 cites W2962749812 @default.
- W3114606989 cites W2962836156 @default.
- W3114606989 cites W2963037989 @default.
- W3114606989 cites W2963091558 @default.
- W3114606989 cites W2963857746 @default.
- W3114606989 cites W2982220924 @default.
- W3114606989 cites W2989604896 @default.
- W3114606989 cites W2989611864 @default.
- W3114606989 cites W2992240579 @default.
- W3114606989 cites W2995801068 @default.
- W3114606989 cites W2998940023 @default.
- W3114606989 cites W3003295287 @default.
- W3114606989 cites W3009818596 @default.
- W3114606989 cites W3011688396 @default.
- W3114606989 cites W3015146731 @default.
- W3114606989 cites W3036271496 @default.
- W3114606989 cites W3098218837 @default.
- W3114606989 cites W3105553032 @default.
- W3114606989 cites W3106228955 @default.
- W3114606989 cites W3125372245 @default.
- W3114606989 cites W639708223 @default.
- W3114606989 doi "https://doi.org/10.1109/jstars.2020.3046482" @default.
- W3114606989 hasPublicationYear "2021" @default.
- W3114606989 type Work @default.
- W3114606989 sameAs 3114606989 @default.
- W3114606989 citedByCount "26" @default.
- W3114606989 countsByYear W31146069892021 @default.
- W3114606989 countsByYear W31146069892022 @default.
- W3114606989 countsByYear W31146069892023 @default.
- W3114606989 crossrefType "journal-article" @default.
- W3114606989 hasAuthorship W3114606989A5023578647 @default.
- W3114606989 hasAuthorship W3114606989A5049747868 @default.
- W3114606989 hasAuthorship W3114606989A5050630882 @default.
- W3114606989 hasAuthorship W3114606989A5054791684 @default.
- W3114606989 hasAuthorship W3114606989A5054800338 @default.
- W3114606989 hasAuthorship W3114606989A5088717109 @default.
- W3114606989 hasBestOaLocation W31146069891 @default.
- W3114606989 hasConcept C127313418 @default.
- W3114606989 hasConcept C153180895 @default.
- W3114606989 hasConcept C154945302 @default.
- W3114606989 hasConcept C178790620 @default.
- W3114606989 hasConcept C185592680 @default.
- W3114606989 hasConcept C2776151529 @default.
- W3114606989 hasConcept C2779227376 @default.
- W3114606989 hasConcept C31972630 @default.
- W3114606989 hasConcept C41008148 @default.
- W3114606989 hasConcept C62649853 @default.
- W3114606989 hasConceptScore W3114606989C127313418 @default.
- W3114606989 hasConceptScore W3114606989C153180895 @default.
- W3114606989 hasConceptScore W3114606989C154945302 @default.
- W3114606989 hasConceptScore W3114606989C178790620 @default.
- W3114606989 hasConceptScore W3114606989C185592680 @default.
- W3114606989 hasConceptScore W3114606989C2776151529 @default.
- W3114606989 hasConceptScore W3114606989C2779227376 @default.
- W3114606989 hasConceptScore W3114606989C31972630 @default.
- W3114606989 hasConceptScore W3114606989C41008148 @default.
- W3114606989 hasConceptScore W3114606989C62649853 @default.
- W3114606989 hasFunder F4320321001 @default.
- W3114606989 hasFunder F4320335777 @default.
- W3114606989 hasLocation W31146069891 @default.
- W3114606989 hasOpenAccess W3114606989 @default.
- W3114606989 hasPrimaryLocation W31146069891 @default.
- W3114606989 hasRelatedWork W1497101000 @default.
- W3114606989 hasRelatedWork W2145985110 @default.
- W3114606989 hasRelatedWork W2547934522 @default.
- W3114606989 hasRelatedWork W2730449274 @default.
- W3114606989 hasRelatedWork W2782964878 @default.
- W3114606989 hasRelatedWork W2922421953 @default.
- W3114606989 hasRelatedWork W2980691083 @default.
- W3114606989 hasRelatedWork W3002270006 @default.
- W3114606989 hasRelatedWork W4281560450 @default.