Lightweight facial landmark detection network based on improved MobileViT

被引:9
作者
Song, Limei [1 ]
Hong, Chuanfei [1 ]
Gao, Tian [1 ]
Yu, Jiali [1 ]
机构
[1] Tiangong Univ, Tianjin Key Lab Intelligent Control Elect Equipmen, Tianjin, Peoples R China
关键词
Facial landmark; MobileViT; Lightweight; Transformer;
D O I
10.1007/s11760-023-02975-4
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The long-distance link between facial landmarks cannot be modeled by the current CNN-based facial landmark detection networks, and these networks typically have many parameters that consume substantial computational resources. This paper proposes a multi-scale lightweight facial landmark detection network with CNN and Transformer multi-branch parallelism. Based on MobileViT, the network incorporates MobileOne Block and simplified Ghost BottleNeck lightweight network structure. Compared to MobileViT on the WFLW dataset, the number of network parameters is reduced by 49.18%, the failure rate is reduced by 3.20%, the detection speed is improved by 41.73%, the FLOPS is reduced by 64.83%, and the NME is improved by 0.45% and 1.31% on the test and pose subsets, respectively. The data proves that the global information extraction of facial landmarks is more accurate after adding the Transformer structure. This paper also compares with other networks, and the result shows that improved MobileViT achieves more accurate detection with fewer model parameters.
引用
收藏
页码:3123 / 3131
页数:9
相关论文
共 50 条
[31]   Facial landmark detection by semi-supervised deep learning [J].
Tang, Xin ;
Guo, Fang ;
Shen, Jianbing ;
Du, Tianyuan .
NEUROCOMPUTING, 2018, 297 :22-32
[32]   LightCDNet: Lightweight Change Detection Network Based on VHR Images [J].
Xing, Yuanjun ;
Jiang, Jiawei ;
Xiang, Jun ;
Yan, Enping ;
Song, Yabin ;
Mo, Dengkui .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2023, 20
[33]   Damage detection of grotto murals based on lightweight neural network [J].
Wu, Ligang ;
Zhang, Liang ;
Shi, Jianhua ;
Zhang, Yu ;
Wan, Jiafu .
COMPUTERS & ELECTRICAL ENGINEERING, 2022, 102
[34]   Optimization of facial expression recognition based on dual attention mechanism by lightweight network model [J].
Fang, Jian ;
Lin, Xiaomei ;
Wu, Yue ;
An, Yi ;
Sun, Haoran .
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2023, 45 (05) :9069-9081
[35]   Lightweight Fatigue Driving Detection Based on Improved YOLOv8 [J].
Sun, Shidong ;
Xu, Yang .
ENGINEERING LETTERS, 2025, 33 (07) :2797-2805
[36]   Research on Lightweight Method of Insulator Target Detection Based on Improved SSD [J].
Zeng, Bing ;
Zhou, Yu ;
He, Dilin ;
Zhou, Zhihao ;
Hao, Shitao ;
Yi, Kexin ;
Li, Zhilong ;
Zhang, Wenhua ;
Xie, Yunmin .
SENSORS, 2024, 24 (18)
[37]   Lightweight Traffic Monitoring Object Detection Algorithm Based on Improved YOLOX [J].
Hu, Weichao ;
Guo, Yuyang ;
Zhang, Qi ;
Chen, Yanyan .
Computer Engineering and Applications, 2024, 60 (07) :167-174
[38]   Lightweight highland barley detection based on improved YOLOv5 [J].
Cai, Minghui ;
Deng, Hui ;
Cai, Jianwei ;
Guo, Weipeng ;
Hu, Zhipeng ;
Yu, Dongzheng ;
Zhang, Houxi .
PLANT METHODS, 2025, 21 (01)
[39]   Lightweight Vehicle Detection Based on Improved YOLOv5s [J].
Wang, Yuhai ;
Xu, Shuobo ;
Wang, Peng ;
Li, Kefeng ;
Song, Ze ;
Zheng, Quanfeng ;
Li, Yanshun ;
He, Qiang .
SENSORS, 2024, 24 (04)
[40]   Lightweight UAV Detection Algorithm Based on Improved YOLOv5 [J].
Peng Y. ;
Tu X. ;
Yang Q. ;
Li R. .
Hunan Daxue Xuebao/Journal of Hunan University Natural Sciences, 2023, 50 (12) :28-38