[1] GIRSHICK RDONAHUE JDARRELL Tet al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Conference on Computer Vision and Pattern Recognition.ColumbusOH:IEEE2014:580-587.
[2] GIRSHICK R.Fast R-CNN[C]//International Conference on Computer Vision (ICCV).Santiago:IEEE2015:1440- 1448.
[3] REN S QHE K MGIRSHICK Ret al.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis & Machine Intelligence201539(6):1137-1149.
[4] CAI Z WVASCONCELOS N.Cascade R-CNN:delving into high quality object detection[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake CityUT:IEEE2018:6154-6162.
[5] REDMON JDIVVALA SGIRSHICK Ret al.You only look once:unifiedreal-time object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition.Las VegasNV:2016:779-788.
[6] LIU WANGUELOV DERHAN Det al.SSD:single shot multibox detector[C]//European Conference on Computer Vision.Cham: Springer2016:21-37.
[7] JOCHER G.Yolov5[Z].Code repository2020.https://github.com/ultralytics/yolov5.
[8] HE K MZHANG X YREN S Qet al.Spatial pyramid pool-ing in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence201537(9):1904-1916.
[9] ZHENG Z HWANG PLIU Wet al.Distance-IoU loss:faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence.[S.l.]:AAAI2020:12993-13000.
[10] MEI Y QFAN Y CZHANG Y Let al.Pyramid attention networks for image restoration[J].ArXiv2020abs/2004. 13824.doi:10.48550/arXiv.2004.13824.
[11] TAN M XPANG R MLE Q V.EfficientDet:scalable and efficient object detection[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition.SeattleWA:IEEE2020:10781-10790.
[12] REZATOFIGHI HTSOI NGWAK J Yet al.Generalized intersection over union:a metric and a loss for bound-ing box regression[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition.Long BeachCA:IEEE 2019:658-666.
[13] XIA G SBAI XDING Jet al.DOTA:a large-scale dataset for object detection in aerial images[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake CityUT:IEEE2018:3974-3983.