Single-Shot Panoptic Segmentation

We present a novel end-to-end single-shot method that segments countable object instances (things) as well as background regions (stuff) into a non-overlapping panoptic segmentation at almost video frame rate. Current state-of-the-art methods are far from reaching video frame rate and mostly rely on merging instance segmentation with semantic background segmentation, making them impractical to use in many applications such as robotics. Our approach relaxes this requirement by using an object detector but is still able to re-solve inter- and intra-class overlaps to achieve a non-overlapping segmentation. On top of a shared encoder-decoder backbone, we utilize multiple branches for semantic segmentation, object detection, and instance center prediction. Finally, our panoptic head combines all outputs into a panoptic segmentation and can even handle conflicting predictions between branches as well as certain false predictions. Our network achieves 32. 6% PQ on MS-COCO at 23. 5 FPS, opening up panoptic segmentation to a broader field of applications.

Authors

• Mark Weber
• Jonathon Luiten
• Bastian Leibe

Keywords

• Visualization
• Semantics
• Merging
• Object detection
• Detectors
• Intelligent robots
• Panoptic Segmentation
• Semantic Segmentation
• False Predictions
• Instance Segmentation
• Segmentation Prediction
• Video Frame Rate
• Final Results
• Bounding Box
• Multi-scale Features
• Two-stage Method
• Post-processing Step
• Multi-task Learning
• L1 Loss
• Speed-accuracy Trade-off
• Feature Pyramid Network
• Scene Understanding
• Semantic Segmentation Task
• Mask R-CNN
• COCO Dataset
• Pyramid Level
• Multi-task Training
• Ground-truth Bounding Box
• Training Configurations