A lightweight deep neural network with higher accuracy

To improve accuracy of the MobileNet network, a new lightweight deep neural network is designed based on the MobileNetV2 network. Firstly, it modifies the network depth of MobileNetV2 to balance the image resolution, network width and depth to keep the gradient stable, which reduces the generation o...

Full description

Saved in:
Bibliographic Details
Published in:PloS one 2022-08, Vol.17 (8), p.e0271225-e0271225
Main Authors: Zhao, Liquan, Wang, Leilei, Jia, Yanfei, Cui, Ying
Format: Article
Language:English
Subjects:
Accuracy
Analysis
Artificial neural networks
Biology and Life Sciences
Channels
Classification
Computer and Information Sciences
Datasets
Engineering and Technology
Fault diagnosis
Feature extraction
Image processing
Image resolution
Lightweight
Modules
Neural networks
Power
Research and Analysis Methods
Social Sciences
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To improve accuracy of the MobileNet network, a new lightweight deep neural network is designed based on the MobileNetV2 network. Firstly, it modifies the network depth of MobileNetV2 to balance the image resolution, network width and depth to keep the gradient stable, which reduces the generation of gradient vanishing or gradient exploding. Secondly, it proposes an improved Bottleneck module by introducing channel attention mechanism. It assigns different weights for different channels according to the degree of relevance between the object features and channels. Therefore, the network can extract more effective features from a complex background. In the end, a new usage strategy of the improved Bottleneck is proposed. It uses the improved Bottleneck module in the second, fourth and fifth stages of MobileNetV2, and uses the original Bottleneck module in other states. Compared with MobileNetV2, MobileNetV3, ShuffleNetV2, GhostNet and HBONetmethods, the proposed method has the highest classification accuracy on the ImageNet-1K dataset, CIFAR-10 and CIFAR-100. Compared with YOLOV4-Lite methods based on these lightweight network networks, YOLOV4-Lite based on our proposed network also has the highest detection accuracy on the PASCAL VOC07+12 dataset.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0271225