Abstract
With the increasing of depth and complexity of the convolutional neural network, parameter dimensionality and volume of computing have greatly restricted its applications. Based on the SqueezeNet network structure, this study introduces a block convolution and uses channel shuffle between blocks to alleviate the information jam. The method is aimed at reducing the dimensionality of parameters of in an original network structure and improving the efficiency of network operation. The verification performance of the ORL dataset shows that the classification accuracy and convergence efficiency are not reduced or even slightly improved when the network parameters are reduced, which supports the validity of block convolution in structure lightweight. Moreover, using a classic CIFAR-10 dataset, this network decreases parameter dimensionality while accelerating computational processing, with excellent convergence stability and efficiency when the network accuracy is only reduced by 1.3%.
Highlights
In the 5G era, with the development of emerging technologies such as the Internet of Things and big data, related applications in smart terminals are becoming more and more widespread
Our work mainly focuses on the intelligent recognition of images and videos, which is an indispensable intelligent application in life
This paper replaces the last 1 × 1 conventional convolution with a grouped convolution to reach the model reduction. It reduced the number of input channels by 1 × 1 grouping convolution in the compression layer before and added batch normalization after the 1 × 1 convolution to speed up the training process
Summary
In the 5G era, with the development of emerging technologies such as the Internet of Things and big data, related applications in smart terminals are becoming more and more widespread. One of the benefits of deep learning frameworks in image recognition is that they do not need the traditional classification algorithms. It requires a lot of artificial processing of image features. Through multilayer convolution and a nonlinear activation function, the algorithm classifies and regresses all image features through MLP [3]. In practical applications such as automatic driving, face recognition on mobile phones, video classification, etc., learning results are often demanded in milliseconds. These devices often have limited processor performance with no prior trainings in the lab. Reducing the calculation parameters and calculation complexity of traditional network frameworks has gained the most research interests in deep learning
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: Computational and Mathematical Methods in Medicine
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.