Weakly Supervised Instance Segmentation using Class Peak Response

CVPR 2018 Yanzhao ZhouYi ZhuQixiang YeQiang QiuJianbin Jiao

Weakly supervised instance segmentation with image-level labels, instead of expensive pixel-level masks, remains unexplored. In this paper, we tackle this challenging problem by exploiting class peak responses to enable a classification network for instance mask extraction... (read more)

PDF Abstract

Evaluation results from the paper

  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.