论文标题
选择性多尺度学习以进行对象检测
Selective Multi-Scale Learning for Object Detection
论文作者
论文摘要
锥体网络是多尺度对象检测的标准方法。当前对特征金字塔网络的研究通常采用层连接来从特征层次结构的某些级别收集特征，并且不考虑它们之间的显着差异。我们提出了一个更好的特征金字塔网络的体系结构，称为选择性多尺度学习（SMSL），以解决此问题。 SMSL是有效且一般的，可以将其集成到单阶段和两阶段检测器中，以提高检测性能，几乎没有额外的推理成本。视网膜与SMSL结合使用可可数据集的AP（从39.1 \％到40.9 \％）获得1.8 \％改善。与SMSL集成时，两个阶段探测器的AP可以提高1.0 \％。
Pyramidal networks are standard methods for multi-scale object detection. Current researches on feature pyramid networks usually adopt layer connections to collect features from certain levels of the feature hierarchy, and do not consider the significant differences among them. We propose a better architecture of feature pyramid networks, named selective multi-scale learning (SMSL), to address this issue. SMSL is efficient and general, which can be integrated in both single-stage and two-stage detectors to boost detection performance, with nearly no extra inference cost. RetinaNet combined with SMSL obtains 1.8\% improvement in AP (from 39.1\% to 40.9\%) on COCO dataset. When integrated with SMSL, two-stage detectors can get around 1.0\% improvement in AP.
