IRTransUNet:用于红外小目标检测的高效变压器嵌入UNet

IF 3.4 3区 物理与天体物理 Q2 INSTRUMENTS & INSTRUMENTATION
Yangjun Pi , Lingchuan Kong , Bo Yang , Rui Chang , Huayan Pu , Mingliang Zhou , Jun Luo
{"title":"IRTransUNet:用于红外小目标检测的高效变压器嵌入UNet","authors":"Yangjun Pi ,&nbsp;Lingchuan Kong ,&nbsp;Bo Yang ,&nbsp;Rui Chang ,&nbsp;Huayan Pu ,&nbsp;Mingliang Zhou ,&nbsp;Jun Luo","doi":"10.1016/j.infrared.2025.106061","DOIUrl":null,"url":null,"abstract":"<div><div>Infrared small target detection is of critical importance in the field of security. However, the inherent weak features and low signal-to-noise ratio of such targets make it particularly difficult to detect them effectively in cluttered and complex backgrounds. To address this issue, this paper proposes IRTransUNet, which integrates local and global information to more thoroughly exploit the differences between the target and the background, thereby achieving more effective discrimination. First, we design a robust feature extractor (RFE), a lightweight and efficient module that leverages a larger contextual receptive field to extract more discriminative fine-grained features. Next, we introduce the IRconvformer module, which focuses on capturing global dependencies and modeling the relationship between the target and background. Specifically, we enhance the target boundary features within tokens using atrous spatial embedding (ASE) and replace the self-attention mechanism with multi-slice linear attention (MSLA), allowing for more efficient global modeling and focused target feature extraction. Additionally, we incorporate a convolutional gated feedforward network (CGFN) to improve the feedforward network, adjusting the information flow between neighboring pixels, thus maintaining the model’s ability to perceive local features. Finally, extensive experiments on four widely used datasets demonstrate that IRTransUNet achieves state-of-the-art performance in infrared small target detection. The code will be publicly available at <span><span>https://github.com/LingchuanK/IRTransUnet</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":13549,"journal":{"name":"Infrared Physics & Technology","volume":"151 ","pages":"Article 106061"},"PeriodicalIF":3.4000,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"IRTransUNet: Efficient transformer embedding UNet for infrared small target detection\",\"authors\":\"Yangjun Pi ,&nbsp;Lingchuan Kong ,&nbsp;Bo Yang ,&nbsp;Rui Chang ,&nbsp;Huayan Pu ,&nbsp;Mingliang Zhou ,&nbsp;Jun Luo\",\"doi\":\"10.1016/j.infrared.2025.106061\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Infrared small target detection is of critical importance in the field of security. However, the inherent weak features and low signal-to-noise ratio of such targets make it particularly difficult to detect them effectively in cluttered and complex backgrounds. To address this issue, this paper proposes IRTransUNet, which integrates local and global information to more thoroughly exploit the differences between the target and the background, thereby achieving more effective discrimination. First, we design a robust feature extractor (RFE), a lightweight and efficient module that leverages a larger contextual receptive field to extract more discriminative fine-grained features. Next, we introduce the IRconvformer module, which focuses on capturing global dependencies and modeling the relationship between the target and background. Specifically, we enhance the target boundary features within tokens using atrous spatial embedding (ASE) and replace the self-attention mechanism with multi-slice linear attention (MSLA), allowing for more efficient global modeling and focused target feature extraction. Additionally, we incorporate a convolutional gated feedforward network (CGFN) to improve the feedforward network, adjusting the information flow between neighboring pixels, thus maintaining the model’s ability to perceive local features. Finally, extensive experiments on four widely used datasets demonstrate that IRTransUNet achieves state-of-the-art performance in infrared small target detection. The code will be publicly available at <span><span>https://github.com/LingchuanK/IRTransUnet</span><svg><path></path></svg></span>.</div></div>\",\"PeriodicalId\":13549,\"journal\":{\"name\":\"Infrared Physics & Technology\",\"volume\":\"151 \",\"pages\":\"Article 106061\"},\"PeriodicalIF\":3.4000,\"publicationDate\":\"2025-08-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Infrared Physics & Technology\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1350449525003548\",\"RegionNum\":3,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"INSTRUMENTS & INSTRUMENTATION\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Infrared Physics & Technology","FirstCategoryId":"101","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1350449525003548","RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"INSTRUMENTS & INSTRUMENTATION","Score":null,"Total":0}
引用次数: 0

摘要

红外小目标检测在安防领域具有十分重要的意义。然而,这类目标固有的微弱特征和低信噪比使得在杂乱复杂的背景下对其进行有效检测尤为困难。为了解决这一问题,本文提出了IRTransUNet,将局部和全局信息相结合,更彻底地利用目标和背景之间的差异,从而实现更有效的识别。首先,我们设计了一个鲁棒特征提取器(RFE),这是一个轻量级和高效的模块,它利用更大的上下文接受场来提取更具区别性的细粒度特征。接下来,我们介绍irconverformer模块,其重点是捕获全局依赖关系并对目标和背景之间的关系进行建模。具体来说,我们使用属性空间嵌入(ASE)增强标记中的目标边界特征,并用多片线性注意(MSLA)取代自注意机制,从而实现更有效的全局建模和集中目标特征提取。此外,我们还引入了卷积门控前馈网络(CGFN)来改进前馈网络,调整相邻像素之间的信息流,从而保持模型感知局部特征的能力。最后,在四个广泛使用的数据集上进行了大量实验,证明IRTransUNet在红外小目标检测方面达到了最先进的性能。代码将在https://github.com/LingchuanK/IRTransUnet上公开。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
IRTransUNet: Efficient transformer embedding UNet for infrared small target detection
Infrared small target detection is of critical importance in the field of security. However, the inherent weak features and low signal-to-noise ratio of such targets make it particularly difficult to detect them effectively in cluttered and complex backgrounds. To address this issue, this paper proposes IRTransUNet, which integrates local and global information to more thoroughly exploit the differences between the target and the background, thereby achieving more effective discrimination. First, we design a robust feature extractor (RFE), a lightweight and efficient module that leverages a larger contextual receptive field to extract more discriminative fine-grained features. Next, we introduce the IRconvformer module, which focuses on capturing global dependencies and modeling the relationship between the target and background. Specifically, we enhance the target boundary features within tokens using atrous spatial embedding (ASE) and replace the self-attention mechanism with multi-slice linear attention (MSLA), allowing for more efficient global modeling and focused target feature extraction. Additionally, we incorporate a convolutional gated feedforward network (CGFN) to improve the feedforward network, adjusting the information flow between neighboring pixels, thus maintaining the model’s ability to perceive local features. Finally, extensive experiments on four widely used datasets demonstrate that IRTransUNet achieves state-of-the-art performance in infrared small target detection. The code will be publicly available at https://github.com/LingchuanK/IRTransUnet.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
5.70
自引率
12.10%
发文量
400
审稿时长
67 days
期刊介绍: The Journal covers the entire field of infrared physics and technology: theory, experiment, application, devices and instrumentation. Infrared'' is defined as covering the near, mid and far infrared (terahertz) regions from 0.75um (750nm) to 1mm (300GHz.) Submissions in the 300GHz to 100GHz region may be accepted at the editors discretion if their content is relevant to shorter wavelengths. Submissions must be primarily concerned with and directly relevant to this spectral region. Its core topics can be summarized as the generation, propagation and detection, of infrared radiation; the associated optics, materials and devices; and its use in all fields of science, industry, engineering and medicine. Infrared techniques occur in many different fields, notably spectroscopy and interferometry; material characterization and processing; atmospheric physics, astronomy and space research. Scientific aspects include lasers, quantum optics, quantum electronics, image processing and semiconductor physics. Some important applications are medical diagnostics and treatment, industrial inspection and environmental monitoring.
×
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