reading : Mask R-CNN(Kaiming He Georgia Gkioxari Piotr Dolla ́r Ross Girshick Facebook AI Research)
abstract
method : Mask R-CNN
在R-CNN中加入一个分支预测object mask(目标掩模)
类似于加了一个分支做bounding box recognition。
a small overhead to faster R-CNN,5 fps
easy to generalize to other task (eg.human pose- 姿态预测)
introduction
Our goal in this work is to develop a compa
原创
2020-07-14 18:31:19 ·
648 阅读 ·
0 评论