TL;DR该研究提出了关系蒸馏网络 (RDN) 的新架构,通过跨物体的空时上下文进行聚合和传播,从而改进了目标检测和跨帧盒子链接,并在 ImageNet VID 数据集上实现了最佳 mAP。
Abstract
It has been well recognized that modeling object-to-object relations would be
helpful for object detection. Nevertheless, the problem is not trivial
especially when exploring the interactions between objects to b