DPNet: Dynamic Pooling Network for Tiny Object Detection

TL;DR

DPNet introduces a dynamic, input-aware downsampling approach with adaptive normalization for tiny object detection, balancing accuracy and computational efficiency in aerial imagery.

Contribution

The paper proposes a novel DPNet architecture with a lightweight predictor and adaptive normalization, enabling flexible downsampling tailored to each input image for improved tiny object detection.

Findings

Reduces GFLOPs by over 35% on TinyCOCO

Maintains detection performance while saving computational resources

Demonstrates effectiveness on TinyCOCO and TinyPerson datasets

Abstract

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.