提升无人机图像小目标检测，兼顾细节保留与上下文信息融合。
MGDFIS: Multi-scale Global-detail Feature Integration Strategy for Small Object Detection
- 设计三层协同模块，实现全局上下文与局部细节的精准融合。
- 在VisDrone上将AP50:95从25.7提升至30.2，AP50达44.2。
- 适合需要高精度小目标检测的无人机视觉任务应用。
无人机影像中的小目标检测需在保留微弱局部特征的同时利用广泛上下文区分微小目标与复杂背景。现有多尺度融合方法虽改善了特征聚合，但常增加计算开销或在多次跨尺度融合中模糊细粒度信息。核心挑战在于平衡低信噪比目标的保持、杂波抑制与高效跨尺度上下文交换。为此，提出颈部级特征融合策略MGDFIS，整合全局上下文交换、局部细节恢复与像素级前景-背景重校准。该策略包含三个协同模块：FusionLock-TSS注意力稳定谱-空间响应，Global-detail Integration结合长程混合与局部细节捕捉，以及Dynamic Pixel Attention对紧凑前景区域重新加权。在可控的VisDrone设置下，YOLO26m + MGDFIS将AP50:95从25.7提升至30.2，AP50从37.2提升至44.2，计算量为96.1 GFLOPs。额外数据集评估显示，在UAVDT上达38.9 AP50和21.9 AP50:95，CARPK上达97.4 AP50。代码已开源：https://github.com/Bai-Xuecheng/MGDFIS。
原文摘要 · Abstract (English)
Small-object detection in Unmanned Aerial Vehicle (UAV) imagery requires preserving weak local evidence while using broader context to separate tiny foreground targets from cluttered backgrounds. Existing multi-scale fusion methods improve feature aggregation, but they often add computation or blur fine details during repeated cross-scale fusion. The central challenge is to balance low-SNR target preservation, clutter suppression, and efficient cross-scale context exchange. To address this challenge, we propose the Multi-scale Global-detail Feature Integration Strategy (MGDFIS), a neck-level feature-fusion strategy that couples global context exchange, local-detail recovery, and pixel-level foreground-background recalibration. MGDFIS integrates three coordinated modules: FusionLock-TSS Attention for stabilizing spectral-spatial responses, Global-detail Integration for combining long-range mixing with local detail capture, and Dynamic Pixel Attention for reweighting compact foreground regions. On the controlled VisDrone setting, YOLO26m + MGDFIS improves AP50:95 from 25.7 to 30.2 and AP50 from 37.2 to 44.2 over the YOLO26m baseline, with 96.1 GFLOPs. Additional dataset-specific evaluations report 38.9 AP50 and 21.9 AP50:95 on UAVDT and 97.4 AP50 on CARPK. The code is available at: https://github.com/Bai-Xuecheng/MGDFIS.
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。