UPSNet: A Unified Panoptic Segmentation Network
| Autor: | Ersin Yumer, Yuwen Xiong, Min Bai, Hengshuang Zhao, Rui Hu, Raquel Urtasun, Renjie Liao |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
050210 logistics & transportation Class (computer programming) Computer science business.industry Deep learning Computer Vision and Pattern Recognition (cs.CV) 05 social sciences Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology Backpropagation Convolution 0502 economics and business 0202 electrical engineering electronic engineering information engineering Code (cryptography) 020201 artificial intelligence & image processing Segmentation Computer vision Artificial intelligence business Representation (mathematics) |
| Zdroj: | CVPR |
| DOI: | 10.48550/arxiv.1901.03784 |
| Popis: | 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 Comment: CVPR 2019 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|