TIIS (한국인터넷정보학회)
Current Result Document :
| 한글제목(Korean Title) |
A new lightweight network based on MobileNetV3 |
| 영문제목(English Title) |
A new lightweight network based on MobileNetV3 |
| 저자(Author) |
Liquan Zhao
Leilei Wang
|
| 원문수록처(Citation) |
VOL 15 NO. 12 PP. 0001 ~ 0015 (2021. 12) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
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. |
| 키워드(Keyword) |
MobileNetV3
Real-time image classification
Lightweight network
Deep convolutional neural network
residual structure
|
| 파일첨부 |
PDF 다운로드
|
