arXiv 2505.232142025-05-29cs.CVcs.AI

SAMamba：用于红外小目标检测的分层视觉自适应状态空间建模

SAMamba: Adaptive State Space Modeling with Hierarchical Vision for Infrared Small Target Detection

School of Artificial Intelligence, Beijing University of Posts and Telecommunications（北京邮电大学人工智能学院）；Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences)（教育部计算电力网络与信息安全重点实验室，山东计算机科学中心（济南国家超算中心），齐鲁工业大学（山东省科学院））；The State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（多模态人工智能系统国家重点实验室，中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Shandong Provincial Key Laboratory of Computer Networks, Shandong Fundamental Research Center for Computer Science（山东省计算机网络重点实验室，山东省计算机科学基础研究中心）

Wenhao Xu, Shuchen Zheng, Changwei Wang, Zherui Zhang, Chuan Ren, Rongtao Xu, Shibiao Xu

备注：: Information Fusion 2025

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出SAMamba框架，结合SAM2分层特征学习与Mamba选择性序列建模，通过FS-Adapter、CSI和DPCF模块解决红外小目标检测中的信息丢失和全局建模低效问题，在多个数据集上显著优于现有方法。

摘要：

红外小目标检测（ISTD）对于军事、海事和预警应用中的远程监控至关重要。ISTD面临的挑战在于目标占据不到0.15%的图像比例，且与复杂背景的区分度低。现有的深度学习方法在降采样过程中常出现信息丢失，且全局上下文建模效率低下。本文提出了SAMamba，一个将SAM2的分层特征学习与Mamba的选择性序列建模相结合的新框架。关键创新包括：（1）特征选择适配器（FS-Adapter），通过双阶段选择（带有可学习任务嵌入的token级和通道级自适应变换）实现高效的从自然到红外的域适应；（2）跨通道状态空间交互（CSI）模块，利用选择性状态空间建模以线性复杂度进行高效的全局上下文建模；（3）细节保留上下文融合（DPCF）模块，通过门控机制自适应结合多尺度特征，以平衡高分辨率和低分辨率特征的贡献。SAMamba通过弥合域差距、保持细粒度细节和高效建模长程依赖来解决ISTD核心挑战。在NUAA-SIRST、IRSTD-1k和NUDT-SIRST数据集上的实验表明，SAMamba显著优于现有最先进方法，特别是在具有异构背景和不同目标尺度的挑战性场景中。代码：https://github.com/zhengshuchen/SAMamba。

英文摘要：

Infrared small target detection (ISTD) is vital for long-range surveillance in military, maritime, and early warning applications. ISTD is challenged by targets occupying less than 0.15% of the image and low distinguishability from complex backgrounds. Existing deep learning methods often suffer from information loss during downsampling and inefficient global context modeling. This paper presents SAMamba, a novel framework integrating SAM2's hierarchical feature learning with Mamba's selective sequence modeling. Key innovations include: (1) A Feature Selection Adapter (FS-Adapter) for efficient natural-to-infrared domain adaptation via dual-stage selection (token-level with a learnable task embedding and channel-wise adaptive transformations); (2) A Cross-Channel State-Space Interaction (CSI) module for efficient global context modeling with linear complexity using selective state space modeling; and (3) A Detail-Preserving Contextual Fusion (DPCF) module that adaptively combines multi-scale features with a gating mechanism to balance high-resolution and low-resolution feature contributions. SAMamba addresses core ISTD challenges by bridging the domain gap, maintaining fine-grained details, and efficiently modeling long-range dependencies. Experiments on NUAA-SIRST, IRSTD-1k, and NUDT-SIRST datasets show SAMamba significantly outperforms state-of-the-art methods, especially in challenging scenarios with heterogeneous backgrounds and varying target scales. Code: https://github.com/zhengshuchen/SAMamba.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。