动态调整图像下采样率，高效检测小目标。
DPNet: Dynamic Pooling Network for Tiny Object Detection
- 根据输入图像自适应调整下采样率，减少计算开销。
- 在TinyCOCO和TinyPerson上分别节省35%和25%的GFLOPs。
- 适合无人机等资源受限场景的小目标检测任务。
在复杂环境下的无人飞行系统中，准确检测小目标至关重要。常规通过缩放图像提升小目标检测精度的方法会显著增加计算成本和负样本数量，严重降低检测性能。本文提出动态池化网络（DPNet），通过引入可调节因子df，将固定下采样过程改为可调策略。设计轻量级预测器为每张输入图预测df，以动态降低骨干网络特征图分辨率，实现输入感知下采样。同时设计自适应归一化模块（ANM）使统一检测器兼容不同df。引导损失监督预测器训练。实验表明，DPNet在TinyCOCO和TinyPerson数据集上分别节省超过35%和25%的GFLOPs，同时保持相当的检测性能。代码将公开。
原文摘要 · Abstract (English)
In unmanned aerial systems, especially in complex environments, accurately detecting tiny objects is crucial. Resizing images is a common strategy to improve detection accuracy, particularly for small objects. However, simply enlarging images significantly increases computational costs and the number of negative samples, severely degrading detection performance and limiting its applicability. This paper proposes a Dynamic Pooling Network (DPNet) for tiny object detection to mitigate these issues. DPNet employs a flexible down-sampling strategy by introducing a factor (df) to relax the fixed downsampling process of the feature map to an adjustable one. Furthermore, we design a lightweight predictor to predict df for each input image, which is used to decrease the resolution of feature maps in the backbone. Thus, we achieve input-aware downsampling. We also design an Adaptive Normalization Module (ANM) to make a unified detector compatible with different dfs. A guidance loss supervises the predictor's training. DPNet dynamically allocates computing resources to trade off between detection accuracy and efficiency. Experiments on the TinyCOCO and TinyPerson datasets show that DPNet can save over 35% and 25% GFLOPs, respectively, while maintaining comparable detection performance. The code will be made publicly available.
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。