[1] [1] REDMON JFARHADI A.YOLOv3:an incremental improvement［DB/OL］.(20180408)［20230801］.https://arxiv.org/abs/1804.02767.

[2] [2] BOCHKOVSKIY AWANG C YLIAO H Y M.YOLOv4:optimal speed and accuracy of object detection［DB/OL］.(20200423)［20230801］.https://arxiv.org/abs/2004.10934.

[3] [3] WANG C YBOCHKOVSKIY ALIAO H Y M.ScaledYOLOv4:scaling cross stage partial network［C］//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Nashville:IEEE2021:1302413033.

[4] [4] GE ZLIU S TWANG Fet al.YOLOX:exceeding YOLO series in 2021［DB/OL］.(20210806)［20230801］.https://arxiv.org/abs/2107.08430.

[5] [5] LONG XDENG KWANG Get al.PPYOLO:an effective and efficient implementation of object detector［DB/OL］.(20200803)［20230801］.https://arxiv.org/abs/2007.12099.

[6] [6] HUANG XWANG X XLYU W Yet al.PPYOLOv2:a practical object detector［DB/OL］.(20220706)［20230801］.https://arxiv.org/abs/2104.10419v1.

[7] [7] XU S LWANG X ZLYU W Yet al.PPYOLOE:an evolved version of YOLO［DB/OL］.(20221212)［20230801］.https://arxiv.org/abs/2203.16250v3.

[8] [8] JOCHER G.YOLOv5 by ultralytics (Version 7.0)［EB/OL］.(20221112)［20231016］.https://doi.org/10.5281/zenodo.3908559.

[9] [9] LI C YLI L LJIANG H Let al.YOLOv6:a singlestage object detection framework for industrial applications［DB/OL］.(20180907)［20230801］.https://arxiv.org/abs/2209.02976.

[10] [10] LI C YLI L LCENG Y Fet al.YOLOv6 v3.0:a fullscale reloading［EB/OL］.(20230113)［20230801］.https://arxiv.org/abs/2301.05586.

[11] [11] WANG C YBOCHKOVSKIY ALIAO H Y M.YOLOv7:trainable bagoffreebies sets new stateoftheart for realtime object detectors［C］//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Vancouver:IEEE2023.doi:10.1109/CVPR52729.2023.00721.

[12] [12] JOCHER GCHAURASIA AQIU J.Ultralytics YOLO (Version 8.0.0) ［EB/OL］.(20230110)［20231016］.https://github.com/ultralytics/ultralytics.

[13] [13] XU X ZJIANG Y QCHEN W Het al.DAMOYOLO:a report on realtime object detection design［DB/OL］(20230317)［20230801］.https://arxiv.org/abs/2211.15444v3.

[18] [18] LI XWANG W HWU L Jet al.Generalized focal loss:learning qualified and distributed bounding boxes for dense object detection［C］//NIPS20:Proceedings of the 34th International Conference on Neural Information Processing Systems.Red Hook:Curran Associates Inc.2020:2100221012.

[19] [19] SHU C YLIU Y FGAO J Fet al.Channelwise knowledge distillation for dense prediction［C］//2021 IEEE/CVF International Conference on Computer Vision (ICCV).Montreal:IEEE2021.doi:10.1109/ICCV48922.2021.00526.

[20] [20] HE K MZHANG X YREN S Qet al.Deep residual learning for image recognition［C］//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas:IEEE2016.doi:10.1109/CVPR.2016.90.

[21] [21] WANG C YLIAO H Y MWU Y Het al.CSPNet:a new backbone that can enhance learning capability of CNN［C］//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).Seattle:IEEE2020.doi:10.1109/CVPRW50498.2020.00203.

[22] [22] LEE YHWANG J WLEE S,et al.An energy and GPUcomputation efficient backbone network for realtime object detection［C］//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).Long Beach:IEEE2019.doi:10.1109/CVPRW.2019.00103.

[23] [23] RAO L.TreeNet:a lightweight oneshot aggregation convolutional network［DB/OL］.(20210925)［20230801］.https://arxiv.org/abs/2109.12342v1.

[24] [24] GE ZLIU S TLI Z Met al.OTA:optimal transport assignment for object detection［C］//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Nashville:IEEE2021.doi:10.1109/CVPR46437.2021.00037.

[25] [25] FENG C JZHONG Y JGAO Yet al.TOOD:taskaligned onestage object detection［C］//2021 IEEE/CVF International Conference on Computer Vision (ICCV).Montreal:IEEE2021.doi:10.1109/ICCV48922.2021.00349.