arXiv 2605.249282026-10-08cs.CV

MambaDSF：基于膨胀特征融合的多尺度SSM用于声纳小目标检测

MambaDSF: Multi-Scale SSM with Dilated Feature Fusion for Sonar Small Target Detection

School of Information Science and Engineering, Ocean University of China（中国海洋大学信息科学与工程学院）；School of Information and Communication Technology, Griffith University（格里菲斯大学信息与通信技术学院）

Hui Lin, Jiayi Li, Jing Wang, Shenghui Rong

备注：: 8 pages, 4 figures, under review at IEEE Geoscience and Remote Sensing Letters (GRSL)

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对声纳小目标检测中像素覆盖不足、噪声干扰和尺度模糊问题，提出MambaDSF混合框架，通过Mamba增强特征金字塔、膨胀融合编码器和尺度自适应损失函数，在UATD数据集上达到91.5% mAP50，参数28.7M。

摘要：

声纳成像是水下目标检测的主要方式，但由于像素覆盖不足、声学对比度低以及不同成像距离下的尺度模糊，小目标仍然难以检测。基于CNN的检测器能高效提取局部特征，但缺乏全局声学上下文，无法抑制噪声引起的虚警。基于Transformer的方法以二次计算代价捕捉长距离依赖。现有的基于Mamba的视觉模型提供高效的线性代价扫描，但缺乏跨金字塔层级的多尺度语义对齐、多感受野融合以及可靠声纳检测所需的小目标感知训练监督。本文提出Mamba膨胀尺度融合（MambaDSF），一个混合框架，通过三个贡献解决这些局限：Mamba增强特征金字塔（MambaEFP）骨干网络，以线性复杂度联合捕捉局部回波线索和全局声学上下文；膨胀融合Mamba（DFMamba）编码器，强制跨金字塔层级的多尺度特征对齐；以及尺度自适应加权IoU（SA-WIoU）和跨尺度一致性（CSC）损失，稳定小目标训练。MambaDSF在UATD前视声纳基准上达到91.5% mAP50，参数为2870万，超越所有对比检测器。在小目标子集上，增益达到+2.2个百分点，在FLS和MD-FLS上的跨域评估证实了所提出架构的泛化能力。代码公开于https://github.com/IDontKnowAAA/MambaDSF。

英文摘要：

Sonar imaging is the primary modality for underwater target detection, yet small targets remain difficult to detect due to insufficient pixel coverage, low acoustic contrast, and scale ambiguity across imaging ranges. CNN-based detectors extract local features efficiently but cannot suppress noise-induced false alarms without global acoustic context. Transformer-based methods capture long-range dependencies at quadratic computational cost. Existing Mamba-based vision models offer efficient linear-cost scanning but lack multi-scale semantic alignment across pyramid levels, multi-receptive-field fusion, and small-target-aware training supervision needed for reliable sonar detection. This letter proposes Mamba Dilated-Scale Fusion (MambaDSF), a hybrid framework addressing these limitations through three contributions: a Mamba Enhanced Feature Pyramid (MambaEFP) backbone that jointly captures local echo cues and global acoustic context at linear complexity; a Dilate Fusion Mamba (DFMamba) encoder that enforces multi-scale feature alignment across pyramid levels; and Scale-Adaptive Weighted IoU (SA-WIoU) and Cross-Scale Coherence (CSC) losses that stabilize small-target training. MambaDSF achieves 91.5% mAP50 on the UATD forward-looking sonar benchmark with 28.7 million parameters, surpassing all compared detectors. On a small-target subset the gain reached +2.2 percentage points, and cross-domain evaluation on FLS and MD-FLS confirms the generalization of the proposed architecture. The codes are publicly available at https://github.com/IDontKnowAAA/MambaDSF.

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。