Self-supervised Scale Equivariant Network for Weakly Supervised Semantic Segmentation

9 Sep 2019Yude WangJie ZhangMeina KanShiguang ShanXilin Chen

Weakly supervised semantic segmentation has attracted much research interest in recent years considering its advantage of low labeling cost. Most of the advanced algorithms follow the design principle that expands and constrains the seed regions from class activation maps (CAM)... (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.