A new lightweight network based on MobileNetV3

被引：19
作者：
Zhao, Liquan [1 ]
Wang, Leilei [1 ]
机构：
[1] Northeast Elect Power Univ, Minist Educ, Key Lab Modern Power Syst Simulat & Control & Ren, Jilin 132012, Jilin, Peoples R China
来源：
KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS | 2022年 / 16卷 / 01期
基金：
中国国家自然科学基金;
关键词：
MobileNetV3; Real-time image classification; Lightweight network; Deep convolutional neural network; residual structure;
D O I：
10.3837/tiis.2022.01.001
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
The MobileNetV3 is specially designed for mobile devices with limited memory and computing power. To reduce the network parameters and improve the network inference speed, a new lightweight network is proposed based on MobileNetV3. Firstly, to reduce the computation of residual blocks, a partial residual structure is designed by dividing the input feature maps into two parts. The designed partial residual structure is used to replace the residual block in MobileNetV3. Secondly, a dual-path feature extraction structure is designed to further reduce the computation of MobileNetV3. Different convolution kernel sizes are used in the two paths to extract feature maps with different sizes. Besides, a transition layer is also designed for fusing features to reduce the influence of the new structure on accuracy. The CIFAR-100 dataset and Image Net dataset are used to test the performance of the proposed partial residual structure. The ResNet based on the proposed partial residual structure has smaller parameters and FLOPs than the original ResNet. The performance of improved MobileNetV3 is tested on CIFAR-10, CIFAR-100 and ImageNet image classification task dataset. Comparing MobileNetV3, GhostNet and MobileNetV2, the improved MobileNetV3 has smaller parameters and FLOPs. Besides, the improved MobileNetV3 is also tested on CPU and Raspberry Pi. It is faster than other networks
引用
收藏
页码：1 / 15
页数：15
相关论文
共 30 条
[1]   Data-Free Learning of Student Networks [J].
Chen, Hanting ;
Wang, Yunhe ;
Xu, Chang ;
Yang, Zhaohui ;
Liu, Chuanjian ;
Shi, Boxin ;
Xu, Chunjing ;
Xu, Chao ;
Tian, Qi .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :3513-3521
[2]   Xception: Deep Learning with Depthwise Separable Convolutions [J].
Chollet, Francois .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :1800-1807
[3]   Multi-view document clustering based on geometrical similarity measurement [J].
Diallo, Bassoma ;
Hu, Jie ;
Li, Tianrui ;
Khan, Ghufran Ahmad ;
Hussein, Ahmed Saad .
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2022, 13 (03) :663-675
[4]   AutoGAN: Neural Architecture Search for Generative Adversarial Networks [J].
Gong, Xinyu ;
Chang, Shiyu ;
Jiang, Yifan ;
Wang, Zhangyang .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :3223-3233
[5]   GhostNet: More Features from Cheap Operations [J].
Han, Kai ;
Wang, Yunhe ;
Tian, Qi ;
Guo, Jianyuan ;
Xu, Chunjing ;
Xu, Chang .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, :1577-1586
[6]  
Han S, 2015, ADV NEUR IN, V28
[7]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[8]   Channel Pruning for Accelerating Very Deep Neural Networks [J].
He, Yihui ;
Zhang, Xiangyu ;
Sun, Jian .
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, :1398-1406
[9]  
Howard A.G., 2017, MOBILENETS EFFICIENT
[10]   Searching for MobileNetV3 [J].
Howard, Andrew ;
Sandler, Mark ;
Chu, Grace ;
Chen, Liang-Chieh ;
Chen, Bo ;
Tan, Mingxing ;
Wang, Weijun ;
Zhu, Yukun ;
Pang, Ruoming ;
Vasudevan, Vijay ;
Le, Quoc V. ;
Adam, Hartwig .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :1314-1324
123