FCOS: A Simple and Strong Anchor-Free Object Detector

IEEE Transactions on Pattern Analysis and Machine Intelligence(2022)

引用 286|浏览574
暂无评分
摘要
In computer vision, object detection is one of most important tasks, which underpins a few instance-level recognition tasks and many downstream applications. Recently one-stage methods have gained much attention over two-stage approaches due to their simpler design and competitive performance. Here we propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per...
更多
查看译文
关键词
Detectors,Task analysis,Object detection,Training,Head,Magnetic heads,Semantics
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要