轻量级模型高效检测遥感图像中的小目标。
A lightweight detector for real-time detection of remote sensing images
- 双分支结构分离局部与全局特征，提升小目标感知能力。
- 在VisDrone2019和NWPU VHR-10上实现高精度与低延迟平衡。
- 适合资源受限的实时遥感监测场景，如无人机巡检。
遥感图像广泛应用于多个领域，但因小目标多且需兼顾精度与效率，实时检测仍具挑战。为此，我们提出专为遥感小目标检测设计的轻量级实时检测器DMG-YOLO。其骨干网络引入双分支特征提取（DFE）模块，将特征图分为两个并行分支：一个通过深度可分离卷积提取局部特征，另一个利用带门控机制的视觉变换器捕捉全局上下文。此外，采用带空洞卷积的多尺度特征融合（MFF）模块增强多尺度信息整合，同时保留细粒度细节。在颈部结构中，提出全局-局部聚合特征金字塔网络（GLAFPN），通过融合全局与局部特征进一步提升小目标检测性能。在VisDrone2019与NWPU VHR-10数据集上的大量实验表明，DMG-YOLO在mAP、模型大小等关键指标上表现优异。
原文摘要 · Abstract (English)
Remote sensing imagery is widely used across various fields, yet real-time detection remains challenging due to the prevalence of small objects and the need to balance accuracy with efficiency. To address this, we propose DMG-YOLO, a lightweight real-time detector tailored for small object detection in remote sensing images. Specifically, we design a Dual-branch Feature Extraction (DFE) module in the backbone, which partitions feature maps into two parallel branches: one extracts local features via depthwise separable convolutions, and the other captures global context using a vision transformer with a gating mechanism. Additionally, a Multi-scale Feature Fusion (MFF) module with dilated convolutions enhances multi-scale integration while preserving fine details. In the neck, we introduce the Global and Local Aggregate Feature Pyramid Network (GLAFPN) to further boost small object detection through global-local feature fusion. Extensive experiments on the VisDrone2019 and NWPU VHR-10 datasets show that DMG-YOLO achieves competitive performance in terms of mAP, model size, and other key metrics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。