PRNet通过保留原始浅层特征提升无人机小目标检测精度。
PRNet: Original Information Is All You Have
- 利用主干网络复用与迭代优化对齐空间与语义信息
- 在VisDrone等数据集上实现更高准确率与效率平衡
- 适合需要实时小目标检测的无人机视觉系统
无人机图像中的小目标检测因特征提取过程中的信息退化而面临挑战，浅层空间细节难以与语义信息有效对齐，导致漏检和误报频发。现有基于FPN的方法依赖后处理增强，但重建细节常偏离原始图像信息，阻碍与语义内容融合。为此，我们提出PRNet，一个实时检测框架，强调原始浅层空间特征的保留与高效利用，以增强小目标表征。PRNet通过两个模块实现：用于空间-语义对齐的渐进式精炼颈（PRN），通过主干网络复用与迭代优化；以及用于下采样时保留浅层信息的增强切片采样（ESSamp），通过优化重排与卷积实现。在VisDrone、AI-TOD和UAVDT数据集上的大量实验表明，PRNet在相近计算约束下优于现有最优方法，实现了更优的精度-效率权衡。
原文摘要 · Abstract (English)
Small object detection in aerial images suffers from severe information degradation during feature extraction due to limited pixel representations, where shallow spatial details fail to align effectively with semantic information, leading to frequent misses and false positives. Existing FPN-based methods attempt to mitigate these losses through post-processing enhancements, but the reconstructed details often deviate from the original image information, impeding their fusion with semantic content. To address this limitation, we propose PRNet, a real-time detection framework that prioritizes the preservation and efficient utilization of primitive shallow spatial features to enhance small object representations. PRNet achieves this via two modules:the Progressive Refinement Neck (PRN) for spatial-semantic alignment through backbone reuse and iterative refinement, and the Enhanced SliceSamp (ESSamp) for preserving shallow information during downsampling via optimized rearrangement and convolution. Extensive experiments on the VisDrone, AI-TOD, and UAVDT datasets demonstrate that PRNet outperforms state-of-the-art methods under comparable computational constraints, achieving superior accuracy-efficiency trade-offs.
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。