Corpus ID: 214802390

EfficientPS: Efficient Panoptic Segmentation

@article{Mohan2020EfficientPSEP,
  title={EfficientPS: Efficient Panoptic Segmentation},
  author={Rohit Mohan and Abhinav Valada},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.02307}
}
  • Rohit Mohan, Abhinav Valada
  • Published 2020
  • Computer Science
  • ArXiv
  • Understanding the scene in which an autonomous robot operates is critical for its competent functioning. Such scene comprehension necessitates recognizing instances of traffic participants along with general scene semantics which can be effectively addressed by the panoptic segmentation task. In this paper, we introduce the Efficient Panoptic Segmentation (EfficientPS) architecture that consists of a shared backbone which efficiently encodes and fuses semantically rich multi-scale features. We… CONTINUE READING

    Citations

    Publications citing this paper.

    MOPT: Multi-Object Panoptic Tracking

    VIEW 20 EXCERPTS
    CITES METHODS & BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 87 REFERENCES

    Panoptic Segmentation

    VIEW 15 EXCERPTS
    HIGHLY INFLUENTIAL

    UPSNet: A Unified Panoptic Segmentation Network

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Seamless Scene Segmentation

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Attention-Guided Unified Network for Panoptic Segmentation

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    An End-To-End Network for Panoptic Segmentation

    VIEW 1 EXCERPT

    Describing the scene as a whole: Joint object detection, scene classification and semantic segmentation

    VIEW 1 EXCERPT

    AdapNet: Adaptive semantic segmentation in adverse environmental conditions

    VIEW 1 EXCERPT

    Weakly- and Semi-Supervised Panoptic Segmentation

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL