针对无人机图像小目标检测，SOD-YOLO提升精度36.1%。
SOD-YOLO: Enhancing YOLO-Based Detection of Small Objects in UAV Imagery
- 在YOLOv8基础上加入ASF机制与P2检测层，增强多尺度特征融合。
- VisDrone2019-DET数据集上mAP₅₀:₉₅提升36.1%，mAP₅₀提升20.6%。
- 适合无人机场景下小目标检测，代码开源可复现。
小目标检测仍是目标检测领域的挑战。为此，我们提出基于YOLOv8的增强模型SOD-YOLO。该模型在特征融合层引入ASF机制以增强多尺度特征融合，添加小目标检测层（命名为P2）以提供更高分辨率特征图，从而提升小目标检测能力，并采用Soft-NMS优化置信度评分，保留真正阳性样本。实验结果表明，SOD-YOLO显著提升检测性能，在VisDrone2019-DET数据集上相较基线模型实现36.1%的mAP$_{50:95}$提升和20.6%的mAP$_{50}$提升。这些改进使SOD-YOLO成为无人机影像中小目标检测的实用高效解决方案。源代码、超参数及模型权重已公开于https://github.com/iamwangxiaobai/SOD-YOLO。
原文摘要 · Abstract (English)
Small object detection remains a challenging problem in the field of object detection. To address this challenge, we propose an enhanced YOLOv8-based model, SOD-YOLO. This model integrates an ASF mechanism in the neck to enhance multi-scale feature fusion, adds a Small Object Detection Layer (named P2) to provide higher-resolution feature maps for better small object detection, and employs Soft-NMS to refine confidence scores and retain true positives. Experimental results demonstrate that SOD-YOLO significantly improves detection performance, achieving a 36.1% increase in mAP$_{50:95}$ and 20.6% increase in mAP$_{50}$ on the VisDrone2019-DET dataset compared to the baseline model. These enhancements make SOD-YOLO a practical and efficient solution for small object detection in UAV imagery. Our source code, hyper-parameters, and model weights are available at https://github.com/iamwangxiaobai/SOD-YOLO.
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。