June 18, 2018
Learning to Segment Every Thing
Computer Vision and Pattern Recognition (CVPR)
The goal of this paper is to propose a new partially supervised training paradigm, together with a novel weight transfer function, that enables training instance segmentation models on a large set of categories all of which have box annotations, but only a small fraction of which have mask annotations.
By: Ronghang Hu, Piotr Dollar, Kaiming He, Trevor Darrell, Ross Girshick