MFP-YOLOv11: A Multi-Scale Feature Fusion YOLOv11 Variant for Object Detection in Complex Road Scenes

Engineering notes

Experimental results on the SODA10M dataset show that MFP-YOLOv11 achieves an mAP@0.5 of 0.697 and an mAP@0.5:0.95 of 0.483, corresponding to absolute gains of 7.0 and 5.7 percentage points over the YOLOv11 baseline, respectively.

Chinese explanation / 中文解读

中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。

Original abstract

As autonomous-driving scenarios become increasingly complex, object detection in road environments remains challenging, especially for small-scale, visually ambiguous, and partially occluded targets. These difficulties are closely related to the loss of fine-grained spatial information caused by repeated downsampling and the limited consistency of multi-scale feature fusion. To address these issues, this paper proposes MFP-YOLOv11 (Multi-dimensional Focused P2 YOLOv11), a YOLOv11-based detector with enhanced multi-scale feature fusion for complex road-scene object detection. The proposed method improves the YOLOv11 architecture from the perspectives of high-resolution feature preservation, deep contextual representation, and multi-scale feature fusion consistency. Specifically, a Multi-Scale Dynamic Alignment Feature Fusion module (MDAF) is designed as the main fusion component to enhance multi-scale feature representation by modelling channel-, spatial-, and scale-level relationships among features at different resolutions. In addition, C3Ghost is selectively employed in shallow high-resolution stages to partially offset the additional computational cost introduced by the enhanced architecture, AIFI-RepBN is introduced to strengthen deep contextual representation, and Detect-P2 is added to provide high-resolution prediction compensation for small-scale object detection. Experimental results on the SODA10M dataset show that MFP-YOLOv11 achieves an mAP@0.5 of 0.697 and an mAP@0.5:0.95 of 0.483, corresponding to absolute gains of 7.0 and 5.7 percentage points over the YOLOv11 baseline, respectively. Comparative experiments, ablation studies, component-wise analysis, and qualitative visualizations show the contribution of the proposed modifications to detection performance in representative complex road scenes. Cross-dataset testing on the KITTI dataset further evaluates the performance of the proposed method under heterogeneous road-scene distributions. Overall, MFP-YOLOv11 improves Recall and mAP in complex road-scene object detection, while introducing higher computational complexity than the original baseline model.

Links and sources

Comments