Detecting small objects in complex scenes, such as those captured by drones, is a daunting challenge due to the difficulty in capturing the complex features of small targets. While the YOLO family has achieved great success in large target detection, its performance is less than satisfactory when faced with small targets. Because of this, this paper proposes a revolutionary model SL-YOLO (Stronger and Lighter YOLO) that aims to break the bottleneck of small target detection. We propose the Hierarchical Extended Path Aggregation Network (HEPAN), a pioneering cross-scale feature fusion method that can ensure unparalleled detection accuracy even in the most challenging environments. At the same time, without sacrificing detection capabilities, we design the C2fDCB lightweight module and add the SCDown downsampling module to greatly reduce the model's parameters and computational complexity. Our experimental results on the VisDrone2019 dataset reveal a significant improvement in performance, with [email protected] jumping from 43.0% to 46.9% and [email protected]:0.95 increasing from 26.0% to 28.9%. At the same time, the model parameters are reduced from 11.1M to 9.6M, and the FPS can reach 132, making it an ideal solution for real-time small object detection in resource-constrained environments.

翻译：在复杂场景（例如无人机拍摄的场景）中检测小目标是一项艰巨的挑战，因为难以捕捉小目标的复杂特征。尽管YOLO系列模型在大目标检测方面取得了巨大成功，但在面对小目标时其性能却不尽如人意。为此，本文提出了一种革命性的模型SL-YOLO（更强更轻的YOLO），旨在突破小目标检测的瓶颈。我们提出了层次化扩展路径聚合网络（HEPAN），这是一种开创性的跨尺度特征融合方法，即使在最具挑战性的环境中也能确保无与伦比的检测精度。同时，在不牺牲检测能力的前提下，我们设计了C2fDCB轻量化模块并添加了SCDown下采样模块，以大幅降低模型的参数量和计算复杂度。我们在VisDrone2019数据集上的实验结果表明，模型性能得到了显著提升，[email protected]从43.0%跃升至46.9%，[email protected]:0.95从26.0%提升至28.9%。同时，模型参数量从11.1M减少到9.6M，FPS可达132，使其成为资源受限环境下实时小目标检测的理想解决方案。