基于Shuffle Attention相似目标检测——以SA-YOLOv7为例
(1.江西理工大学 软件工程学院,江西 南昌 330013;2.广东尼古拉能源科技有限公司,广东 广州 510700)
摘要
YOLOv7在目标检测中取得了优异的效果,但对相似物体的检测仍存在误检率较高的问题,其主要原因是YOLOv7对细粒度特征的提取能力不足。为解决上述问题,该研究提出SA-YOLOv7目标检测网络,即在不改变ELAN(Extend Efficient Layer Aggregation Networks)整体结构的前提下,将注意力模块SA(Shuffle Attention)与之融合,形成SA-ELAN模块,以获取更多通道和空间特征信息,进而提高相似物体的检测精确度。模型在公共的手和手套相似物体数据集上开展了大量对比实验,探究了SA加入YOLOv7网络中的数量及位置对结果的影响,揭示了SA发挥作用的底层原理,深化了对注意力机制的理解。实验结果显示:SA-YOLOv7相较于YOLOv7,检测精度提升了7.7%,mAP@0.5:0.95提高了1.8%,与最新的YOLOv11相比,也具有0.9%的检测精度优势。SA-YOLOv7的研究为相似物体检测技术的发展提供了助力。
关键词
深度学习;YOLOv7;Shuffle Attention;相似目标检测
参考文献
- [1] 周志华.机器学习 [M].北京:清华大学出版社,2016.
- [2] HU J,SHEN L,ALBANIE S,et al. Squeeze-and-Excitation Networks [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(8):2011-2023.
- [3] HOU Q B,ZHOU D Q,FENG J S. Coordinate Attention for Efficient Mobile Network Design [C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Nashville:IEEE,2021:13708-13717.
- [4] LI X,HU X L,YANG J. Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks [J/OL].arXiv:1905.09646 [cs.CV].[2025-01-03]https://doi.org/10.48550/arXiv.1905.09646.
- [5] WOO S,PARK J,LEE J Y,et al. CBAM: Convolutional Block Attention Module [C]//Computer Vision-ECCV 2018: 15th European Conference.Munich:Springer,2018:3-19.
- [6] 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,2023:7464-7475.
- [7] WANG C Y,LIAO H Y M,YEH I H. Designing Network Design Strategies Through Gradient Path Analysis [J/OL].arXiv:2211.04800 [cs.CV].[2024-12-25].https://doi.org/10.48550/arXiv.2211.04800.
- [8] ZHANG Q L,YANG Y B. SA-Net: Shuffle Attention for Deep Convolutional Neural Networks [C]//ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).Toronto:IEEE,2021:2235-2239.
- [9] 邱锡鹏.神经网络与深度学习 [M].北京:机械工业出版社,2020.
- [10] LI X,WANG W H,HU X L,et al. Selective Kernel Networks [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Long Beach:IEEE,2019:510-519.
- [11] WANG Q,WU B G,ZHU P F,et al. ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks [C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Seattle:IEEE,2020:11531-11539.
- [12] OUYANG D L,HE S,ZHANG G Z,et al. Efficient Multi-Scale Attention Module with Cross-Spatial Learning [C]//ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).Rhodes Island:IEEE,2023:1-5.
- [13] KRIZHEVSKY A,SUTSKEVER I,HINTON G E. ImageNet Classification with Deep Convolutional Neural Networks [J].Communications of the ACM,2017,60(6):84-90.
- [14] SIMONYAN K,ZISSERMAN A. Very Deep Convolutional Networks for Large-Scale Image Recognition [J/OL].arXiv:1409.1556 [cs.CV].[2024-12-26].https://doi.org/10.48550/arXiv.1409.1556.
- [15] SZEGEDY C,LIU W,JIA Y Q,et al. Going Deeper with Convolutions [J/OL].arXiv:1409.4842 [cs.CV].[2024-12-28].https://doi.org/10.48550/arXiv.1409.4842.
- [16] 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,2016:770-778.
- [17] HUANG G,LIU Z,MAATEN L V D,et al. Densely Connected Convolutional Networks [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu:IEEE,2017:2261-2269.
- [18] 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,2019:752-760.
- [19] 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,2020:1571-1580.
- [20] WANG C Y,BOCHKOVSKIY A,LIAO H Y M. Scaled-YOLOv4: Scaling Cross Stage Partial Network [C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Nashville:IEEE,2021:13024-13033.
- [21] WU Y X,HE K M. Group Normalization [C]// Computer Vision-ECCV 2018: 15th European Conference.Munich:Springer,2018:3-19.
- [22] MA N N,ZHANG X Y,ZHENG H T,et al. ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design [C]//Computer Vision-ECCV 2018: 15th European Conference.Munich:Springer,2018:122-138.
- [23] 董洪义.深度学习之PyTorch物体检测实战 [M].北京:机械工业出版社,2020.
- [24] 伊恩·古德费洛,约书亚·本吉奥,亚伦·库维尔.深度学习 [M].北京:人民邮电出版社,2017.
- [25] NIU Z Y,ZHONG G Q,YU H. A Review on the Attention Mechanism of Deep Learning [J].Neurocomputing,2021,452:48-62.
基金项目
江西省大学生创新创业训练计划项目(202310407035)
作者简介
任昱臻(2001—),男,汉族,山西晋中人,本科,研究方向:机器视觉;樊中奎(1980—),男,汉族,江西南昌人,讲师,硕士研究生,研究方向:人工智能;冯振营(1985—),男,汉族,广东广州人,助理工程师,本科,研究方向:图像处理;朱梅(1980—),女,汉族,江西南昌人,实验师,硕士研究生,研究方向:模式识别。