论文标题
SSFPN：比例顺序（S^2）基于特征 - 特征金字塔网络用于对象检测
ssFPN: Scale Sequence (S^2) Feature Based-Feature Pyramid Network for Object Detection
论文作者
论文摘要
特征金字塔网络（FPN）是对象检测模型的重要模块，以考虑对象的各种尺度。但是，小物体上的平均精度（AP）相对较低，低于中等和大对象上的AP。原因是CNN较深层导致信息丢失作为特征提取水平的原因。我们提出了一个新的比例顺序（S^2）特征FPN的提取，以增强小物体的特征信息。我们将FPN结构视为尺度空间和提取尺度序列（S^2）特征，该特征是在FPN的水平轴上通过3D卷积。它基本上是扩展不变的功能，并建立在小物体的高分辨率金字塔特征图上。此外，建议的S^2功能可以扩展到基于FPN的大多数对象检测模型。我们证明所提出的S2功能可以提高COCO数据集中一阶段和两阶段探测器的性能。根据提出的S2功能，我们分别为Yolov4-P5和Yolov4-P6获得了高达AP改善的1.3％和1.1％。对于更快的RCNN和Mask R-CNN，我们分别在建议的S^2功能的情况下观察到AP改善的2.0％和1.6％。
Feature Pyramid Network (FPN) has been an essential module for object detection models to consider various scales of an object. However, average precision (AP) on small objects is relatively lower than AP on medium and large objects. The reason is why the deeper layer of CNN causes information loss as feature extraction level. We propose a new scale sequence (S^2) feature extraction of FPN to strengthen feature information of small objects. We consider FPN structure as scale-space and extract scale sequence (S^2) feature by 3D convolution on the level axis of FPN. It is basically scale invariant feature and is built on high-resolution pyramid feature map for small objects. Furthermore, the proposed S^2 feature can be extended to most object detection models based on FPN. We demonstrate the proposed S2 feature can improve the performance of both one-stage and two-stage detectors on MS COCO dataset. Based on the proposed S2 feature, we achieve upto 1.3% and 1.1% of AP improvement for YOLOv4-P5 and YOLOv4-P6, respectively. For Faster RCNN and Mask R-CNN, we observe upto 2.0% and 1.6% of AP improvement with the suggested S^2 feature, respectively.
