Similar Object Detection Based on Shuffle Attention —Taking SA-YOLOv7 as an Example
(1.School of Software Engineering, Jiangxi University of Science and Technology, Nanchang 330013, China; 2.Guangdong Nikola Energy Technology Co., Ltd., Guangzhou 510700, China)
Abstract
YOLOv7 achieves excellent results in object detection, but there is still a problem of high false detection rate in similar object detection. The main reason is that YOLOv7 has insufficient ability to extract fine-grained features. To solve the above problems, this study proposes a SA-YOLOv7 object detection network. Specifically, without changing the overall structure of ELAN, the attention module SA is merged with it to form a SA-ELAN module to obtain more channel and spatial feature information, thereby improving the detection accuracy of similar objects. The model conducts a large number of comparative experiments on public hand and glove similar object datasets, explores the influence of the number and position of SA added to the YOLOv7 network on the results. It also reveals the underlying principle of SA's role and deepens the understanding of the Attention Mechanism. The experimental results show that the detection accuracy of SA-YOLOv7 is 7.7% higher than that of YOLOv7, and its mAP@0.5:0.95 is 1.8% higher than that of YOLOv7. Compared with the latest YOLOv11, it also has a 0.9% detection accuracy advantage. The research on SA-YOLOv7 provides assistance for the development of similar object detection technology.
Keywords
Deep Learning; YOLOv7; Shuffle Attention; similar Object Detection
References
- [1] Zhou Zhihua Machine Learning [M]. Beijing: Tsinghua University Press, 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] Qiu Xipeng Neural Networks and Deep Learning [M]. Beijing: Machinery Industry Press, 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] Dong Hongyi PyTorch Object Detection Practice in Deep Learning [M]. Beijing: Machinery Industry Press, 2020
- Ian Goodfellow, Joshua Bengio, Aaron Cowell Deep Learning [M]. Beijing: People's Posts and Telecommunications Press, 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.
Funding
Innovation and Entrepreneurship Training Program for College Students in Jiangxi Province (202310407035)
About the authors
Ren Yuzhen (2001-), male, Han ethnicity, from Jinzhong, Shanxi Province, bachelor's degree, research direction: machine vision; Fan Zhongkui (1980-), male, Han ethnicity, from Nanchang, Jiangxi, lecturer, master's student, research direction: artificial intelligence; Feng Zhenying (1985-), male, Han ethnicity, from Guangzhou, Guangdong, assistant engineer, bachelor's degree, research direction: image processing; Zhu Mei (1980-), female, Han ethnicity, born in Nanchang, Jiangxi, is an experimenter and master's student. Her research direction is pattern recognition.