论文标题
双重细化功能用于对象检测的金字塔网络
Dual Refinement Feature Pyramid Networks for Object Detection
论文作者
论文摘要
FPN是对象检测器中使用的常见组件，它通过相邻级别的插值和求和来补充多尺度信息。但是，由于存在非线性操作和具有不同输出尺寸的卷积层，不同级别之间的关系要复杂得多，因此像素的总和不是有效的方法。在本文中，我们首先分析了从像素级别和特征地图级别的设计缺陷。然后，我们针对问题设计了一个名为Dual Refinempt特征金字塔网络（DRFPN）的新型无参数特征金字塔网络。具体而言，DRFPN由两个模块组成：空间改进块（SRB）和通道改进块（CRB）。 SRB根据相邻级别之间的上下文信息了解采样点的位置和内容。 CRB根据注意机制学习了一种自适应通道合并方法。我们提出的DRFPN可以轻松地插入现有的基于FPN的模型中。对于两阶段探测器，没有铃铛和哨子，我们的模型在可可检测基准上的表现优于不同的基于FPN的对应物，而在可可分割基准上，在可可检测基准上优于1.6至2.2 ap。对于一阶段探测器，DRFPN将基于锚固的视网膜AP提高了1.9 AP，并在使用Resnet50作为骨架时，将无锚的FCO提高了1.3 AP。广泛的实验验证了DRFPN的鲁棒性和泛化能力。该代码将公开可用。
FPN is a common component used in object detectors, it supplements multi-scale information by adjacent level features interpolation and summation. However, due to the existence of nonlinear operations and the convolutional layers with different output dimensions, the relationship between different levels is much more complex, the pixel-wise summation is not an efficient approach. In this paper, we first analyze the design defects from pixel level and feature map level. Then, we design a novel parameter-free feature pyramid networks named Dual Refinement Feature Pyramid Networks (DRFPN) for the problems. Specifically, DRFPN consists of two modules: Spatial Refinement Block (SRB) and Channel Refinement Block (CRB). SRB learns the location and content of sampling points based on contextual information between adjacent levels. CRB learns an adaptive channel merging method based on attention mechanism. Our proposed DRFPN can be easily plugged into existing FPN-based models. Without bells and whistles, for two-stage detectors, our model outperforms different FPN-based counterparts by 1.6 to 2.2 AP on the COCO detection benchmark, and 1.5 to 1.9 AP on the COCO segmentation benchmark. For one-stage detectors, DRFPN improves anchor-based RetinaNet by 1.9 AP and anchor-free FCOS by 1.3 AP when using ResNet50 as backbone. Extensive experiments verifies the robustness and generalization ability of DRFPN. The code will be made publicly available.
