Lightweight CNN for HRRP Recognition Based on Attention Mechanism Structured Pruning

Yanhua Wang, Zhilong Zhang, Mingchen Yuan, Jiandong Liao, Liang Zhang*

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Deep convolutional neural network (CNN) has been widely investigated for radar target high resolution range profile (HRRP) recognition. However, the deep structures of CNN require high storage and computational capabilities, thus restricting its applications with limited resources. In this paper, we design a lightweight CNN model with structure pruning based on the channel-wise attention mechanism. Specifically, the attention value is used to represent the importance of the filters in CNN. Furthermore, Greedy strategy and fine-tuning are adopted in the pruning process to minimize the loss of model performance. The results of public dataset show that the recognition accuracy of the proposed method decreases by less than 0.13% when the pruning ratio is 80%.

源语言英语
主期刊名2023 IEEE International Radar Conference, RADAR 2023
出版商Institute of Electrical and Electronics Engineers Inc.
ISBN(电子版)9781665482783
DOI
出版状态已出版 - 2023
活动2023 IEEE International Radar Conference, RADAR 2023 - Sydney, 澳大利亚
期限: 6 11月 202310 11月 2023

出版系列

姓名Proceedings of the IEEE Radar Conference
ISSN(印刷版)1097-5764
ISSN(电子版)2375-5318

会议

会议2023 IEEE International Radar Conference, RADAR 2023
国家/地区澳大利亚
Sydney
时期6/11/2310/11/23

指纹

探究 'Lightweight CNN for HRRP Recognition Based on Attention Mechanism Structured Pruning' 的科研主题。它们共同构成独一无二的指纹。

引用此