ScopeMamba-YOLO：内外拓宽感知范围用于遥感图像中的小目标检测
ScopeMamba-YOLO: Widening the Perceptual Scope Inward and Outward for Small Object Detection in Remote Sensing Imagery
- Nanjing University of Science and Technology（南京理工大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出ScopeMamba-YOLO，采用路径外零门控选择性扫描解耦上下文建模，通过CGCM和SS-PAN增强小目标检测，在VisDrone和AI-TOD上以更少参数取得显著精度提升。
AI中文摘要：
在无人机（UAV）和遥感图像中进行小目标检测，需要在保持高分辨率细节的同时建模长距离上下文。增加步长为4的检测层并移除步长为32的阶段有利于微小目标，但会削弱外围空间支持，而直接将选择性扫描插入主特征路径可能会干扰微弱的局部线索。我们提出了ScopeMamba-YOLO，其核心是一种路径外、零门控的选择性扫描原理，将上下文建模与卷积流解耦。该原理通过骨干网络中的级联全局上下文模块（CGCM）和颈部中的选择性扫描路径聚合网络（SS-PAN）实例化。自适应多尺度条带（AMS）模块降低了高分辨率特征提取的成本，而尺度自适应DFL（SA-DFL）头仅以0.008M额外参数重新分配跨尺度的分布支持和回归能力。受控实验表明，匹配的主路径选择性扫描使mAP50降低0.98个百分点，而路径外的CGCM在三个种子的无CGCM均值基础上将最终配置提升了0.67个百分点；操作控制表明，这一增益不能仅由辅助分支容量解释。ERF分析进一步表明，完整的上下文路径在步长为8时将外围能量比从0.008提高到0.090。在VisDrone-2019上，ScopeMamba-S以3.57M参数达到50.8%的mAP50，超过YOLOv8s 10.8个百分点，同时仅使用其32%的参数；ScopeMamba-M以6.48M参数达到52.6%的mAP50。在AI-TOD上也观察到一致的改进，特别是对于非常微小和微小的目标。
英文摘要：
Small object detection in unmanned aerial vehicle (UAV) and remote sensing imagery requires preserving high-resolution detail while modeling long-range context. Adding a stride-4 detection level and removing the stride-32 stage benefits tiny targets but weakens peripheral spatial support, whereas directly inserting selective scanning into the main feature path can interfere with weak local cues. We propose ScopeMamba-YOLO, built around an off-path, zero-gated selective-scanning principle that decouples contextual modeling from the convolutional stream. The principle is instantiated by a Cascaded Global-Context Module (CGCM) in the backbone and a Selective-Scan PAN (SS-PAN) in the neck. An Adaptive Multi-scale Strip (AMS) Block reduces the cost of high-resolution feature extraction, while a Scale-Adaptive DFL (SA-DFL) head reallocates distributional support and regression capacity across scales with only 0.008M additional parameters. Controlled experiments show that matched main-path selective scanning reduces mAP50 by 0.98 pp, whereas off-path CGCM improves the final configuration by 0.67 pp over the three-seed no-CGCM mean; operator controls indicate that this gain is not explained by auxiliary branch capacity alone. ERF analysis further shows that the complete context pathway increases the peripheral energy ratio from 0.008 to 0.090 at stride 8. On VisDrone-2019, ScopeMamba-S achieves 50.8% mAP50 with 3.57M parameters, exceeding YOLOv8s by 10.8 pp while using 32% of its parameters; ScopeMamba-M reaches 52.6% mAP50 with 6.48M parameters. Consistent improvements are also observed on AI-TOD, especially for very-tiny and tiny objects.
