Multiscale Channel Attention and Cross-Layer Fusion Network for Infrared Small Target Detection

Shengli Zhou;Tong Liu;Xiaolu Guo;Meibo Lv
{"title":"Multiscale Channel Attention and Cross-Layer Fusion Network for Infrared Small Target Detection","authors":"Shengli Zhou;Tong Liu;Xiaolu Guo;Meibo Lv","doi":"10.1109/LGRS.2025.3580709","DOIUrl":null,"url":null,"abstract":"Infrared small target detection (IRSTD) faces challenges due to limited global perception and feature ambiguity in complex scenarios. To address these issues, we propose a novel multiscale channel attention and cross-layer fusion network (MACFNet). The framework integrates three key innovations: 1)the feature convolution attention transformer (FCAT) addresses limited global perception by combining local features and global contexts to enhance target representation; 2) the efficient channel and spatial attention (ECSA) module resolves feature ambiguity by optimizing discriminative feature weighting; and 3) an enhanced M-UNet architecture incorporates channelwise cross fusion transformer (CCT) modules to enable effective cross-scale semantic alignment. Extensive experiments on the SIRST and NUDT-SIRST datasets demonstrate the state-of-the-art performance, achieving significantly higher IoU of 0.8396 and 0.9346, respectively, surpassing the existing model-driven and data-driven methods while maintaining a real-time capable inference speed of 29.7167 FPS.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0000,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/11039771/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Infrared small target detection (IRSTD) faces challenges due to limited global perception and feature ambiguity in complex scenarios. To address these issues, we propose a novel multiscale channel attention and cross-layer fusion network (MACFNet). The framework integrates three key innovations: 1)the feature convolution attention transformer (FCAT) addresses limited global perception by combining local features and global contexts to enhance target representation; 2) the efficient channel and spatial attention (ECSA) module resolves feature ambiguity by optimizing discriminative feature weighting; and 3) an enhanced M-UNet architecture incorporates channelwise cross fusion transformer (CCT) modules to enable effective cross-scale semantic alignment. Extensive experiments on the SIRST and NUDT-SIRST datasets demonstrate the state-of-the-art performance, achieving significantly higher IoU of 0.8396 and 0.9346, respectively, surpassing the existing model-driven and data-driven methods while maintaining a real-time capable inference speed of 29.7167 FPS.
红外小目标检测的多尺度通道关注和跨层融合网络
在复杂场景下,红外小目标检测面临全局感知受限和特征模糊的挑战。为了解决这些问题,我们提出了一种新的多尺度通道关注和跨层融合网络(MACFNet)。该框架集成了三个关键创新:1)特征卷积注意转换器(FCAT)通过结合局部特征和全局上下文来解决有限的全局感知问题,以增强目标表示;2)高效通道与空间注意(ECSA)模块通过优化判别性特征权重来解决特征歧义;3)增强的M-UNet体系结构集成了信道交叉融合变压器(CCT)模块,以实现有效的跨尺度语义对齐。在SIRST和NUDT-SIRST数据集上的大量实验证明了最先进的性能,IoU分别达到了0.8396和0.9346,超过了现有的模型驱动和数据驱动方法,同时保持了29.7167 FPS的实时推理速度。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信