高级检索

  • ISSN 1006-3080
  • CN 31-1691/TQ

基于MAML算法的YOLOv3目标检测模型

沈震宇 朱昌明 王喆

沈震宇, 朱昌明, 王喆. 基于MAML算法的YOLOv3目标检测模型[J]. 华东理工大学学报(自然科学版). doi: 10.14135/j.cnki.1006-3080.20201128002
引用本文: 沈震宇, 朱昌明, 王喆. 基于MAML算法的YOLOv3目标检测模型[J]. 华东理工大学学报(自然科学版). doi: 10.14135/j.cnki.1006-3080.20201128002
SHEN Zhenyu, ZHU Changming, WANG Zhe. YOLOv3 Object Detection Model Based on MAML Algorithm[J]. Journal of East China University of Science and Technology. doi: 10.14135/j.cnki.1006-3080.20201128002
Citation: SHEN Zhenyu, ZHU Changming, WANG Zhe. YOLOv3 Object Detection Model Based on MAML Algorithm[J]. Journal of East China University of Science and Technology. doi: 10.14135/j.cnki.1006-3080.20201128002

基于MAML算法的YOLOv3目标检测模型

doi: 10.14135/j.cnki.1006-3080.20201128002
基金项目: 晨光计划(18CG54);中国博士后科学基金(2019M651576);国家自然科学青年基金(61602296);上海市自然科学基金(16ZR1414500)
详细信息
    作者简介:

    沈震宇(1996—),男,上海嘉定人,硕士生,主要研究方向为目标检测。E-mail:564669672@qq.com

    通讯作者:

    朱昌明,E-mail:cmzhu@shmtu.edu.cn

    王 喆,E-mail:wangzhe@ecust.edu.cn

  • 中图分类号: TP391.4

YOLOv3 Object Detection Model Based on MAML Algorithm

  • 摘要: 作为典型的一体化卷积神经网络,YOLOv3模型的网路传输途径简单,检测速度相对较快,但检测精度较低。当遇到新的目标在训练数据集中存在的样本较少时,模型检测会更加不准确,甚至会出现检测不到的情况。本文基于与模型不相关的元学习算法(MAML)改进了YOLOv3主干网络的结构,使其具有内循环和外循环的梯度下降,在初始参数基础上进行多步的梯度调整,达到仅用小样本数据就能快速收敛的目的。实验结果表明,该方法使得YOLOv3模型的检测精度提升了5.24%,且可以使梯度下降保持稳定,有效地满足YOLOv3模型在小样本数据训练情况下识别目标位置的精准性和泛化性。

     

  • 图  1  MAML训练网络结构流程图

    Figure  1.  Structure of MAML training network

    图  2  YOLOv3的样本分类结果

    Figure  2.  Classification results of YOLOv3

    图  3  基于MAML的YOLOv3的样本分类结果

    Figure  3.  Classification results of YOLOv3 based on MAML

    图  4  YOLOv3模型的AP值

    Figure  4.  AP value of YOLOv3

    图  5  基于MAML的YOLOv3模型的AP值

    Figure  5.  AP value of YOLOv3 based on MAML

    图  6  冻结网络层训练的损失函数曲线变化

    Figure  6.  Change curves of training loss of frozen network layer

    图  7  解冻网络层训练的损失函数曲线变化

    Figure  7.  Change curves of training loss of thawing network layer

    图  8  基于MAML的YOLOv3预测结果

    Figure  8.  Prediction results of YOLOv3 model based on MAML

    表  1  分类结果的精确度比较结果

    Table  1.   Accuracy of classification results

    ModelPercision/%mAP/%
    YOLOv350.774.81
    YOLOv3 with MAML56.680.05
    下载: 导出CSV
  • [1] FAN Q, ZHUO W, TANG C K, et al. Few-shot object detection with attention-RPN and multi-relation detector[C]//2020 IEEE Conference on Computer Vision and Pattern Recognition. USA: IEEE, 2020: 4012-4021.
    [2] WANG T, ZHANG X P, YUAN L, et al. Few-shot adaptive faster R-CNN[C]//2019 IEEE Conference on Computer Vision and Pattern Recognition. USA: IEEE, 2019: 7166-7175.
    [3] 王鹏, 陆振宇, 詹天明, 等. 基于PDSSD改进型神经网络的小目标检测算法[J]. 计算机应用与软件, 2021, 38(1): 149-191.
    [4] FINN C, ABBEEL P, LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks[C]//Proceedings of the 34th International Conference on Machine Learning. USA: ACM, 2017: 1126-1135.
    [5] 李雅倩, 盖成远, 肖存军, 等. 基于细化多尺度深度特征的目标检测网络[J]. 电子学报, 2020, 48(12): 2360-2366.
    [6] REDMON J, FARHADI A. YOLOv3: An incremental improvement[EB/OL]. arXiv. org, (2018-04-08)[2019-04-01]. https://arXiv.org/abs/1804.02767.
    [7] BOCHKOVSKIY A, WANG C Y, LIAO H Y. YOLOv4: Optimal speed and accuracy of object detection[EB/OL]. arXiv. org, (2020-04-23)[2020-09-16]. https://arxiv.org/abs/2004.10934.
    [8] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. USA: IEEE, 2014: 580-587.
    [9] HE K M, ZHANG X Y, REN S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916. doi: 10.1109/TPAMI.2015.2389824
    [10] GIRSHICK R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision. Chile: IEEE, 2015: 1440-1448.
    [11] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[C]//2015 International Conference on Neural Information Processing Systems. [s.l.]:[s.n.], 2015: 91-99.
    [12] LIN T, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//2017 IEEE International Conference on Computer Vision. USA: IEEE, 2017: 2117-2125.
    [13] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. USA: IEEE, 2016: 779-788.
    [14] LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single shot multibox detector[C]//European Conference on Computer Vision. Cham: Springer, 2016: 21-37.
    [15] LIN T, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//2017 International Conference on Computer Vision. Italy: IEEE, 2017: 2980-2988.
    [16] TIAN Z, SHEN C H, CHEN H, et al. FCOS: Fully convolutionalone-stage object detection[C]//2019 IEEE International Conference on Computer Vision. Korea: IEEE, 2019: 9626-9635.
    [17] 马振伟, 何高奇, 袁玉波. 基于小样本深度学习的通风柜橱窗状态识别方法[J]. 华东理工大学学报(自然科学版), 2020, 46(3): 428-435.
    [18] REDMON J, FARHADI A. YOLO9000: Better, faster, stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. USA: IEEE, 2017: 7263-7271.
  • 加载中
图(8) / 表(1)
计量
  • 文章访问数:  485
  • HTML全文浏览量:  216
  • PDF下载量:  32
  • 被引次数: 0
出版历程
  • 收稿日期:  2020-11-28
  • 网络出版日期:  2021-03-24

目录

    /

    返回文章
    返回