Multi-scale capsule Swin Transformer-based method for SAR image target recognition

A multi-scale capsule Swin Transformer network (MSCSTN) was proposed by synergizing the semantic feature encoding of capsule units with the context feature mapping of Swin Transformer. Capsule encoding and the Swin Transformer were jointly applied to SAR image target recognition. The network was int...

Full description

Saved in:
Bibliographic Details
Main Authors: HOU Yuchao, WANG Jie, LI Hongtao, HAO Yan, DUAN Xiaoqi, HUANG Kaiwen, TIAN Youliang
Format: Article
Language:zho
Published: Editorial Department of Journal on Communications 2025-03-01
Series:Tongxin xuebao
Subjects:
Online Access:http://www.joconline.com.cn/thesisDetails#10.11959/j.issn.1000-436x.2025045
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850154319550087168
author HOU Yuchao
WANG Jie
LI Hongtao
HAO Yan
DUAN Xiaoqi
HUANG Kaiwen
TIAN Youliang
author_facet HOU Yuchao
WANG Jie
LI Hongtao
HAO Yan
DUAN Xiaoqi
HUANG Kaiwen
TIAN Youliang
author_sort HOU Yuchao
collection DOAJ
description A multi-scale capsule Swin Transformer network (MSCSTN) was proposed by synergizing the semantic feature encoding of capsule units with the context feature mapping of Swin Transformer. Capsule encoding and the Swin Transformer were jointly applied to SAR image target recognition. The network was integrated with three parallel capsule Swin Transformer encoding structures, which were fused to classify the input image. Each structure was constructed through a capsule token encoder based on expanded convolutional slice partition and a 3D capsule Swin Transformer module, which designed to capture of more profound and extensive semantic features.The experimental results on the moving and stationary target acquisition and recognition (MSTAR) dataset and FUSAR-Ship dataset were shown to demonstrate that MSCSTN outperformed other methods under various test conditions. The results demonstrate that MSCSTN exhibits excellent recognition performance, generalization ability, and potential for application.
format Article
id doaj-art-e66dcda574b2475d84f83d61cb08edd0
institution OA Journals
issn 1000-436X
language zho
publishDate 2025-03-01
publisher Editorial Department of Journal on Communications
record_format Article
series Tongxin xuebao
spelling doaj-art-e66dcda574b2475d84f83d61cb08edd02025-08-20T02:25:24ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2025-03-014627429088698488Multi-scale capsule Swin Transformer-based method for SAR image target recognitionHOU YuchaoWANG JieLI HongtaoHAO YanDUAN XiaoqiHUANG KaiwenTIAN YouliangA multi-scale capsule Swin Transformer network (MSCSTN) was proposed by synergizing the semantic feature encoding of capsule units with the context feature mapping of Swin Transformer. Capsule encoding and the Swin Transformer were jointly applied to SAR image target recognition. The network was integrated with three parallel capsule Swin Transformer encoding structures, which were fused to classify the input image. Each structure was constructed through a capsule token encoder based on expanded convolutional slice partition and a 3D capsule Swin Transformer module, which designed to capture of more profound and extensive semantic features.The experimental results on the moving and stationary target acquisition and recognition (MSTAR) dataset and FUSAR-Ship dataset were shown to demonstrate that MSCSTN outperformed other methods under various test conditions. The results demonstrate that MSCSTN exhibits excellent recognition performance, generalization ability, and potential for application.http://www.joconline.com.cn/thesisDetails#10.11959/j.issn.1000-436x.2025045dilated convolution patch partitioncapsule token encoderthree-dimensional capsule Swin Transformer modulemulti scale capsule Swin Transformer networkSAR image target recognition
spellingShingle HOU Yuchao
WANG Jie
LI Hongtao
HAO Yan
DUAN Xiaoqi
HUANG Kaiwen
TIAN Youliang
Multi-scale capsule Swin Transformer-based method for SAR image target recognition
Tongxin xuebao
dilated convolution patch partition
capsule token encoder
three-dimensional capsule Swin Transformer module
multi scale capsule Swin Transformer network
SAR image target recognition
title Multi-scale capsule Swin Transformer-based method for SAR image target recognition
title_full Multi-scale capsule Swin Transformer-based method for SAR image target recognition
title_fullStr Multi-scale capsule Swin Transformer-based method for SAR image target recognition
title_full_unstemmed Multi-scale capsule Swin Transformer-based method for SAR image target recognition
title_short Multi-scale capsule Swin Transformer-based method for SAR image target recognition
title_sort multi scale capsule swin transformer based method for sar image target recognition
topic dilated convolution patch partition
capsule token encoder
three-dimensional capsule Swin Transformer module
multi scale capsule Swin Transformer network
SAR image target recognition
url http://www.joconline.com.cn/thesisDetails#10.11959/j.issn.1000-436x.2025045
work_keys_str_mv AT houyuchao multiscalecapsuleswintransformerbasedmethodforsarimagetargetrecognition
AT wangjie multiscalecapsuleswintransformerbasedmethodforsarimagetargetrecognition
AT lihongtao multiscalecapsuleswintransformerbasedmethodforsarimagetargetrecognition
AT haoyan multiscalecapsuleswintransformerbasedmethodforsarimagetargetrecognition
AT duanxiaoqi multiscalecapsuleswintransformerbasedmethodforsarimagetargetrecognition
AT huangkaiwen multiscalecapsuleswintransformerbasedmethodforsarimagetargetrecognition
AT tianyouliang multiscalecapsuleswintransformerbasedmethodforsarimagetargetrecognition