Real-Time Panoptic Segmentation from Dense Detections
Abstract
Panoptic segmentation is a complex full scene parsing task requiring simultaneous instance and semantic segmentation at high resolution. Current state-of-the-art approaches cannot run in real-time, and simplifying these architectures to improve efficiency severely degrades their accuracy. In this paper, we propose a new single-shot panoptic segmentation network that leverages dense detections and a global self-attention mechanism to operate in real-time with performance approaching the state of the art. We introduce a novel parameter-free mask construction method that substantially reduces computational complexity by efficiently reusing information from the object detection and semantic segmentation sub-tasks. The resulting network has a simple data flow that does not require feature map re-sampling or clustering post-processing, enabling significant hardware acceleration. Our experiments on the Cityscapes and COCO benchmarks show that our network works at 30 FPS on 1024x2048 resolution, trading a 3% relative performance degradation from the current state of the art for up to 440% faster inference.
Cite
@article{arxiv.1912.01202,
title = {Real-Time Panoptic Segmentation from Dense Detections},
author = {Rui Hou and Jie Li and Arjun Bhargava and Allan Raventos and Vitor Guizilini and Chao Fang and Jerome Lynch and Adrien Gaidon},
journal= {arXiv preprint arXiv:1912.01202},
year = {2020}
}
Comments
12 pages, 6 figures