Corpus ID: 208548413

Real-Time Panoptic Segmentation from Dense Detections

@article{Hou2019RealTimePS,
  title={Real-Time Panoptic Segmentation from Dense Detections},
  author={Rui Hou and Jie Li and Arjun Bhargava and Allan Raventos and Vitor Campanholo Guizilini and Chao Fang and Jerome Lynch and Adrien Gaidon},
  journal={ArXiv},
  year={2019},
  volume={abs/1912.01202}
}
  • Rui Hou, Jie Li, +5 authors Adrien Gaidon
  • Published 2019
  • Computer Science
  • ArXiv
  • 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… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 40 REFERENCES

    Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes

    VIEW 1 EXCERPT

    Fast Panoptic Segmentation Network

    VIEW 3 EXCERPTS

    Panoptic Segmentation

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    UPSNet: A Unified Panoptic Segmentation Network

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Panoptic Feature Pyramid Networks

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    An End-To-End Network for Panoptic Segmentation

    VIEW 1 EXCERPT

    Seamless Scene Segmentation

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth

    VIEW 3 EXCERPTS

    DeeperLab: Single-Shot Image Parser

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL