论文标题
FPN中的有效融合因子用于微小对象检测
Effective Fusion Factor in FPN for Tiny Object Detection
论文作者
论文摘要
基于FPN的检测器在一般对象检测中取得了重大进展，例如Coco和Pascal VOC。但是，这些检测器在某些应用程序方案（例如微小的对象检测）中失败。在本文中，我们认为FPN中相邻层之间的自上而下连接带来了两侧影响，不仅是阳性的，因此对微小的对象检测产生了影响。我们提出了一个新颖的概念，即融合因子，以控制深层传递到浅层层的信息，以使FPN适应微小的对象检测。经过一系列的实验和分析，我们探讨了如何通过统计方法估算特定数据集的融合因子的有效值。估计取决于每层分布的对象数量。全面的实验是在微小的对象检测数据集上进行的，例如Tinypers和Tiny Citypersons。我们的结果表明，在使用适当的融合因子配置FPN时，网络能够在微小对象检测数据集上的基线上实现显着的性能提高。代码和模型将发布。
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.
