UPSNet: A Unified Panoptic Segmentation Network
This work solves the problem of unified scene understanding for computer vision applications, representing an incremental advancement by integrating existing methods into a more efficient framework.
The paper tackles the panoptic segmentation task by proposing UPSNet, a unified network that simultaneously addresses semantic and instance segmentation with a novel panoptic head, achieving state-of-the-art performance with faster inference on datasets like Cityscapes and COCO.
In this paper, we propose a unified panoptic segmentation network (UPSNet) for tackling the newly proposed panoptic segmentation task. On top of a single backbone residual network, we first design a deformable convolution based semantic segmentation head and a Mask R-CNN style instance segmentation head which solve these two subtasks simultaneously. More importantly, we introduce a parameter-free panoptic head which solves the panoptic segmentation via pixel-wise classification. It first leverages the logits from the previous two heads and then innovatively expands the representation for enabling prediction of an extra unknown class which helps better resolve the conflicts between semantic and instance segmentation. Additionally, it handles the challenge caused by the varying number of instances and permits back propagation to the bottom modules in an end-to-end manner. Extensive experimental results on Cityscapes, COCO and our internal dataset demonstrate that our UPSNet achieves state-of-the-art performance with much faster inference. Code has been made available at: https://github.com/uber-research/UPSNet