SSAP: Single-Shot Instance Segmentation With Affinity Pyramid

Proposal-free instance segmentation methods mainly generate instance-agnostic semantic labels and instance-aware features to group pixels into different object instances. However, previous mostly employ separate modules for these two sub-tasks require multiple passes inference. In addition the lack of efficiency, also failed perform as well proposal-based approaches. To this end, work proposes a single-shot proposal-free method that requires only one single pass prediction. Our is based on learning an affinity pyramid, which computes probability belong same in hierarchical manner. Moreover, incorporating with learned novel cascaded graph partition (CGP) module presented fuse predictions segment instances efficiently. As additional contribution, we conduct experiment demonstrate benefits capturing detailed structures from finely annotated training examples. approach evaluated Cityscapes COCO datasets achieves state-of-the-art performance.