FPN-based detectors have made significant progress in general object
detection, e.g., MS COCO and PASCAL VOC. However, these detectors fail in
certain application scenarios, e.g., tiny object detection. In this paper, we
argue that the top-down connections between adjacent layers in FPN bring
two-side influences for tiny object detection, not only positive. We propose a
novel concept, fusion factor, to control information that deep layers deliver
to shallow layers, for adapting FPN to tiny object detection. After series of
experiments and analysis, we explore how to estimate an effective value of
fusion factor for a particular dataset by a statistical method. The estimation
is dependent on the number of objects distributed in each layer. Comprehensive
experiments are conducted on tiny object detection datasets, e.g., TinyPerson
and Tiny CityPersons. Our results show that when configuring FPN with a proper
fusion factor, the network is able to achieve significant performance gains
over the baseline on tiny object detection datasets. Codes and models will be
released.

本文分析了在小目标检测过程中，FPN 相邻层之间的自上而下连接产生的双向影响，并提出了一个新的概念 “融合因子”，用于控制深层传递给浅层的信息，以适应小目标检测。我们使用统计方法估计了特定数据集的有效融合因子值，从而在 TinyPerson 和 Tiny CityPersons 数据集上获得显著的性能提升。

FPN 中小目标检测的有效融合因素

Effective Fusion Factor in FPN for Tiny Object Detection

In this technical report, we present our solutions of Waymo Open Dataset
(WOD) Challenge 2020 - 2D Object Track. We adopt FPN as our basic framework.
Cascade RCNN, stacked PAFPN Neck and Double-Head are used for performance
improvements. In order to handle the small object detection problem in WOD, we
use very large image scales for both training and testing. Using our methods,
our team RW-TSDet achieved the 1st place in the 2D Object Detection Track.

本文介绍了我们在 Waymo 开源数据集上使用的解决方案，使用了 FPN、Cascade RCNN、stacked PAFPN Neck 和 Double-Head 等技术对性能进行了提升，在训练和测试中使用了非常大的图像尺度，并使用这些方法，在 2D 物体检测领域获得了第一名。

Waymo Open Dataset Challenge 2020 2D 目标检测赛道第一名方案

1st Place Solutions of Waymo Open Dataset Challenge 2020 -- 2D Object  Detection Track

Feature pyramids are a basic component in recognition systems for detecting
objects at different scales. But recent deep learning object detectors have
avoided pyramid representations, in part because they are compute and memory
intensive. In this paper, we exploit the inherent multi-scale, pyramidal
hierarchy of deep convolutional networks to construct feature pyramids with
marginal extra cost. A top-down architecture with lateral connections is
developed for building high-level semantic feature maps at all scales. This
architecture, called a Feature Pyramid Network (FPN), shows significant
improvement as a generic feature extractor in several applications. Using FPN
in a basic Faster R-CNN system, our method achieves state-of-the-art
single-model results on the COCO detection benchmark without bells and
whistles, surpassing all existing single-model entries including those from the
COCO 2016 challenge winners. In addition, our method can run at 5 FPS on a GPU
and thus is a practical and accurate solution to multi-scale object detection.
Code will be made publicly available.

该论文介绍了基于深度卷积网络的 Feature Pyramid Network（FPN），该网络利用深度卷积网络自带的金字塔多尺度特征，并在多种应用中取得了重大改进，尤其是在目标检测上。使用 FPN 的 Faster R-CNN 系统在 COCO 检测基准测试中取得了最先进的单模型结果。此外，该方法能够在 GPU 上以 5 FPS 的速度运行，是一种实用且准确的多尺度目标检测解决方案。