Reinforced Coloring for End-to-End Instance Segmentation

no code implementations • 14 May 2020 • Tuan Tran Anh, Khoa Nguyen-Tuan, Tran Minh Quan, Won-Ki Jeong

To exploit the advantages of conventional single-object-per-step segmentation methods without impairing the scalability, we propose a novel iterative deep reinforcement learning agent that learns how to differentiate multiple objects in parallel.

Instance Segmentation Object +2