ColorRL: Reinforced Coloring for End-to-End Instance Segmentation

Instance segmentation, the task of identifying and separating each individual object of interest in the image, is one of the actively studied research topics in computer vision. Although many feed-forward networks produce highquality binary segmentation on different types of images, their final result heavily relies on the post-processing step, which separates instances from the binary mask. In comparison, the existing iterative methods extract a single object at a time using discriminative knowledge-based properties (e.g., shapes, boundaries, etc.) without relying on postprocessing. However, they do not scale well with a large number of objects. To exploit the advantages of conventional sequential segmentation methods without impairing the scalability, we propose a novel iterative deep reinforcement learning agent that learns how to differentiate multiple objects in parallel. By constructing a relational graph between pixels, we design a reward function that encourages separating pixels of different objects and grouping pixels that belong to the same instance. We demonstrate that the proposed method can efficiently perform instance segmentation of many objects without heavy post-processing.