Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100616135> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W3100616135 endingPage "3750" @default.
- W3100616135 startingPage "3750" @default.
- W3100616135 abstract "Object detection is one of the core technologies in aerial image processing and analysis. Although existing aerial image object detection methods based on deep learning have made some progress, there are still some problems remained: (1) Most existing methods fail to simultaneously consider multi-scale and multi-shape object characteristics in aerial images, which may lead to some missing or false detections; (2) high precision detection generally requires a large and complex network structure, which usually makes it difficult to achieve the high detection efficiency and deploy the network on resource-constrained devices for practical applications. To solve these problems, we propose a slimmer network for more efficient object detection in aerial images. Firstly, we design a polymorphic module (PM) for simultaneously learning the multi-scale and multi-shape object features, so as to better detect the hugely different objects in aerial images. Then, we design a group attention module (GAM) for better utilizing the diversiform concatenation features in the network. By designing multiple detection headers with adaptive anchors and the above-mentioned two modules, we propose a one-stage network called PG-YOLO for realizing the higher detection accuracy. Based on the proposed network, we further propose a more efficient channel pruning method, which can slim the network parameters from 63.7 million (M) to 3.3M that decreases the parameter size by 94.8%, so it can significantly improve the detection efficiency for real-time detection. Finally, we execute the comparative experiments on three public aerial datasets, and the experimental results show that the proposed method outperforms the state-of-the-art methods." @default.
- W3100616135 created "2020-11-23" @default.
- W3100616135 creator A5005741067 @default.
- W3100616135 creator A5008194767 @default.
- W3100616135 creator A5009238720 @default.
- W3100616135 creator A5024235511 @default.
- W3100616135 creator A5088335237 @default.
- W3100616135 creator A5089132290 @default.
- W3100616135 date "2020-11-14" @default.
- W3100616135 modified "2023-10-03" @default.
- W3100616135 title "A Slimmer Network with Polymorphic and Group Attention Modules for More Efficient Object Detection in Aerial Images" @default.
- W3100616135 cites W2183182206 @default.
- W3100616135 cites W2412782625 @default.
- W3100616135 cites W2613825824 @default.
- W3100616135 cites W2774989306 @default.
- W3100616135 cites W2779335303 @default.
- W3100616135 cites W2804436788 @default.
- W3100616135 cites W2886335102 @default.
- W3100616135 cites W2888527098 @default.
- W3100616135 cites W2890319410 @default.
- W3100616135 cites W2894994475 @default.
- W3100616135 cites W2897898606 @default.
- W3100616135 cites W2901505625 @default.
- W3100616135 cites W2912514498 @default.
- W3100616135 cites W2953867371 @default.
- W3100616135 cites W2981506617 @default.
- W3100616135 cites W2992240579 @default.
- W3100616135 cites W2997900157 @default.
- W3100616135 cites W2999599167 @default.
- W3100616135 cites W3009131247 @default.
- W3100616135 cites W3009818596 @default.
- W3100616135 cites W3009938199 @default.
- W3100616135 cites W3013436129 @default.
- W3100616135 cites W3033983932 @default.
- W3100616135 cites W639708223 @default.
- W3100616135 doi "https://doi.org/10.3390/rs12223750" @default.
- W3100616135 hasPublicationYear "2020" @default.
- W3100616135 type Work @default.
- W3100616135 sameAs 3100616135 @default.
- W3100616135 citedByCount "12" @default.
- W3100616135 countsByYear W31006161352021 @default.
- W3100616135 countsByYear W31006161352022 @default.
- W3100616135 countsByYear W31006161352023 @default.
- W3100616135 crossrefType "journal-article" @default.
- W3100616135 hasAuthorship W3100616135A5005741067 @default.
- W3100616135 hasAuthorship W3100616135A5008194767 @default.
- W3100616135 hasAuthorship W3100616135A5009238720 @default.
- W3100616135 hasAuthorship W3100616135A5024235511 @default.
- W3100616135 hasAuthorship W3100616135A5088335237 @default.
- W3100616135 hasAuthorship W3100616135A5089132290 @default.
- W3100616135 hasBestOaLocation W31006161351 @default.
- W3100616135 hasConcept C114614502 @default.
- W3100616135 hasConcept C115961682 @default.
- W3100616135 hasConcept C153180895 @default.
- W3100616135 hasConcept C154945302 @default.
- W3100616135 hasConcept C2776151529 @default.
- W3100616135 hasConcept C2776429412 @default.
- W3100616135 hasConcept C2781238097 @default.
- W3100616135 hasConcept C31972630 @default.
- W3100616135 hasConcept C33923547 @default.
- W3100616135 hasConcept C41008148 @default.
- W3100616135 hasConcept C87619178 @default.
- W3100616135 hasConceptScore W3100616135C114614502 @default.
- W3100616135 hasConceptScore W3100616135C115961682 @default.
- W3100616135 hasConceptScore W3100616135C153180895 @default.
- W3100616135 hasConceptScore W3100616135C154945302 @default.
- W3100616135 hasConceptScore W3100616135C2776151529 @default.
- W3100616135 hasConceptScore W3100616135C2776429412 @default.
- W3100616135 hasConceptScore W3100616135C2781238097 @default.
- W3100616135 hasConceptScore W3100616135C31972630 @default.
- W3100616135 hasConceptScore W3100616135C33923547 @default.
- W3100616135 hasConceptScore W3100616135C41008148 @default.
- W3100616135 hasConceptScore W3100616135C87619178 @default.
- W3100616135 hasIssue "22" @default.
- W3100616135 hasLocation W31006161351 @default.
- W3100616135 hasOpenAccess W3100616135 @default.
- W3100616135 hasPrimaryLocation W31006161351 @default.
- W3100616135 hasRelatedWork W1988485990 @default.
- W3100616135 hasRelatedWork W2007544051 @default.
- W3100616135 hasRelatedWork W2095705906 @default.
- W3100616135 hasRelatedWork W2334336442 @default.
- W3100616135 hasRelatedWork W2732308154 @default.
- W3100616135 hasRelatedWork W2975200075 @default.
- W3100616135 hasRelatedWork W3002270006 @default.
- W3100616135 hasRelatedWork W3112953119 @default.
- W3100616135 hasRelatedWork W3162220967 @default.
- W3100616135 hasRelatedWork W3177406559 @default.
- W3100616135 hasVolume "12" @default.
- W3100616135 isParatext "false" @default.
- W3100616135 isRetracted "false" @default.
- W3100616135 magId "3100616135" @default.
- W3100616135 workType "article" @default.