Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309259700> ?p ?o ?g. }
- W4309259700 abstract "In recent studies, remote sensing object detection methods based on deep learning have emerged as a primary concern in environmental monitoring, military investigation, and hazard response. However, many difficulties, such as complex backgrounds, dense target quantities, large-scale variations, and non-uniform distribution, lead to many parameters and complex network structures, thus limiting the accuracy of the detector and slowing the inference speed. To address these issues, we propose a lightweight and efficient object detector for remote sensing images. First, an asymmetric convolution with the visual attention mechanism is reconstructed to decrease the complexity and strengthen the feature representation ability. Then, an adaptive feature selection structure is designed to extract discriminative feature information, which can adaptively model the shapes of objects by introducing deformable convolution to obtain a stronger geometric feature representation. To reduce information loss across different channels and spatial locations, a hybrid receptive field module is also proposed to increase the receptive field model by mixing dilated convolutional layers with different dilation rates. Finally, experimental results on the DIOR dataset show that our approach significantly improves detection accuracy and running speed." @default.
- W4309259700 created "2022-11-25" @default.
- W4309259700 creator A5015463546 @default.
- W4309259700 creator A5029278837 @default.
- W4309259700 creator A5052202989 @default.
- W4309259700 creator A5054410967 @default.
- W4309259700 creator A5054500885 @default.
- W4309259700 creator A5064489177 @default.
- W4309259700 date "2022-11-18" @default.
- W4309259700 modified "2023-10-16" @default.
- W4309259700 title "AFSPNet: an adaptive feature selection pyramid network for efficient object detection in remote sensing images" @default.
- W4309259700 cites W1536680647 @default.
- W4309259700 cites W2002330476 @default.
- W4309259700 cites W2061200049 @default.
- W4309259700 cites W2102605133 @default.
- W4309259700 cites W2194775991 @default.
- W4309259700 cites W2512351403 @default.
- W4309259700 cites W2531409750 @default.
- W4309259700 cites W2570343428 @default.
- W4309259700 cites W2577537809 @default.
- W4309259700 cites W2752782242 @default.
- W4309259700 cites W2913087080 @default.
- W4309259700 cites W2953867371 @default.
- W4309259700 cites W2963037989 @default.
- W4309259700 cites W2963125010 @default.
- W4309259700 cites W2963150697 @default.
- W4309259700 cites W2963163009 @default.
- W4309259700 cites W2963604034 @default.
- W4309259700 cites W2982083293 @default.
- W4309259700 cites W2992240579 @default.
- W4309259700 cites W2995801068 @default.
- W4309259700 cites W2997747012 @default.
- W4309259700 cites W2999452014 @default.
- W4309259700 cites W3009818596 @default.
- W4309259700 cites W3048939508 @default.
- W4309259700 cites W3090239664 @default.
- W4309259700 cites W3106250896 @default.
- W4309259700 cites W3109055651 @default.
- W4309259700 cites W3113164744 @default.
- W4309259700 cites W3114606989 @default.
- W4309259700 cites W3121842289 @default.
- W4309259700 cites W3126489540 @default.
- W4309259700 cites W3132170587 @default.
- W4309259700 cites W3133878118 @default.
- W4309259700 cites W3144293580 @default.
- W4309259700 cites W3172258972 @default.
- W4309259700 cites W3175458168 @default.
- W4309259700 cites W3176495987 @default.
- W4309259700 cites W3196107618 @default.
- W4309259700 cites W3196230185 @default.
- W4309259700 cites W3217197319 @default.
- W4309259700 cites W4200493764 @default.
- W4309259700 cites W4205932092 @default.
- W4309259700 cites W4214648418 @default.
- W4309259700 cites W4292968451 @default.
- W4309259700 cites W639708223 @default.
- W4309259700 doi "https://doi.org/10.1117/1.jrs.16.044512" @default.
- W4309259700 hasPublicationYear "2022" @default.
- W4309259700 type Work @default.
- W4309259700 citedByCount "0" @default.
- W4309259700 crossrefType "journal-article" @default.
- W4309259700 hasAuthorship W4309259700A5015463546 @default.
- W4309259700 hasAuthorship W4309259700A5029278837 @default.
- W4309259700 hasAuthorship W4309259700A5052202989 @default.
- W4309259700 hasAuthorship W4309259700A5054410967 @default.
- W4309259700 hasAuthorship W4309259700A5054500885 @default.
- W4309259700 hasAuthorship W4309259700A5064489177 @default.
- W4309259700 hasConcept C127313418 @default.
- W4309259700 hasConcept C138885662 @default.
- W4309259700 hasConcept C142575187 @default.
- W4309259700 hasConcept C148483581 @default.
- W4309259700 hasConcept C153180895 @default.
- W4309259700 hasConcept C154945302 @default.
- W4309259700 hasConcept C2524010 @default.
- W4309259700 hasConcept C2776151529 @default.
- W4309259700 hasConcept C2776401178 @default.
- W4309259700 hasConcept C31972630 @default.
- W4309259700 hasConcept C33923547 @default.
- W4309259700 hasConcept C41008148 @default.
- W4309259700 hasConcept C41895202 @default.
- W4309259700 hasConcept C45347329 @default.
- W4309259700 hasConcept C50644808 @default.
- W4309259700 hasConcept C52622490 @default.
- W4309259700 hasConcept C59404180 @default.
- W4309259700 hasConcept C62649853 @default.
- W4309259700 hasConcept C76155785 @default.
- W4309259700 hasConcept C94915269 @default.
- W4309259700 hasConcept C97931131 @default.
- W4309259700 hasConceptScore W4309259700C127313418 @default.
- W4309259700 hasConceptScore W4309259700C138885662 @default.
- W4309259700 hasConceptScore W4309259700C142575187 @default.
- W4309259700 hasConceptScore W4309259700C148483581 @default.
- W4309259700 hasConceptScore W4309259700C153180895 @default.
- W4309259700 hasConceptScore W4309259700C154945302 @default.
- W4309259700 hasConceptScore W4309259700C2524010 @default.
- W4309259700 hasConceptScore W4309259700C2776151529 @default.
- W4309259700 hasConceptScore W4309259700C2776401178 @default.
- W4309259700 hasConceptScore W4309259700C31972630 @default.
- W4309259700 hasConceptScore W4309259700C33923547 @default.
- W4309259700 hasConceptScore W4309259700C41008148 @default.