@inproceedings{18afd952c6214958b0c31ffc3e08523c,
title = "A convolutional neural network based on optimized structure and its lightweighting",
abstract = "In this paper, we design a convolutional neural network based on the ideas of depthwise separable convolution and inverted residual module. The scaling factor of BN layer is used as a measure for channel pruning of the network model to compress it. By analyzing the layer-by-layer pruning process of conventional convolution, the layer-by-layer pruning method with depthwise separable convolution and inverted residual structure is proposed to prune the channels of the network model, and finally, the channel pruning strategy of classification simplification network is developed. Tests on the selected dataset showed that the classification accuracy of the pruned and fine-tuned network model is 97.7\% when the pruning rate is 0.7.",
keywords = "Convolutional neural network, channel pruning, depthwise separable convolution, inverted residual structure",
author = "Jinyong Deng and Zhiheng Zhao and Yang Liu and Yongzhe Chen and Zhefan Zhang and Yu Zhang",
note = "Publisher Copyright: {\textcopyright} 2022 SPIE.; 2nd International Conference on Advanced Algorithms and Signal Image Processing, AASIP 2022 ; Conference date: 19-08-2022 Through 21-08-2022",
year = "2022",
doi = "10.1117/12.2659679",
language = "英语",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Kannimuthu Subramaniyam",
booktitle = "Second International Conference on Advanced Algorithms and Signal Image Processing, AASIP 2022",
address = "美国",
}