Unifying Training and Inference for Panoptic Segmentation

@article{Li2020UnifyingTA,
  title={Unifying Training and Inference for Panoptic Segmentation},
  author={Qizhu Li and Xiaojuan Qi and P. Torr},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={13317-13325}
}
  • Qizhu Li, Xiaojuan Qi, P. Torr
  • Published 2020
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
We present an end-to-end network to bridge the gap between training and inference pipeline for panoptic segmentation, a task that seeks to partition an image into semantic regions for "stuff" and object instances for "things". In contrast to recent works, our network exploits a parametrised, yet lightweight panoptic segmentation submodule, powered by an end-to-end learnt dense instance affinity, to capture the probability that any pair of pixels belong to the same instance. This panoptic… Expand
14 Citations
Fully Convolutional Networks for Panoptic Segmentation
  • 2
  • PDF
CASNet: Common Attribute Support Network for image instance and panoptic segmentation
  • PDF
Instance and Panoptic Segmentation Using Conditional Convolutions
  • 1
  • PDF
Occluded Video Instance Segmentation
  • 2
  • PDF
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
  • 64
  • PDF
Learning Category- and Instance-Aware Pixel Embedding for Fast Panoptic Segmentation
  • 1
  • PDF
MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers
  • 18
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 32 REFERENCES
Panoptic Feature Pyramid Networks
  • 225
  • Highly Influential
  • PDF
UPSNet: A Unified Panoptic Segmentation Network
  • 119
  • Highly Influential
  • PDF
Attention-Guided Unified Network for Panoptic Segmentation
  • 101
  • Highly Influential
  • PDF
DeeperLab: Single-Shot Image Parser
  • 63
  • Highly Influential
  • PDF
Decomposed Attention: Self-Attention with Linear Complexities
  • 3
  • Highly Influential
  • PDF
Decomposed attention: Selfattention with linear complexities
  • arXiv preprint arXiv:1812.01243,
  • 2018
Learning to Fuse Things and Stuff
  • 53
  • Highly Influential
  • PDF
Weakly- and Semi-Supervised Panoptic Segmentation
  • 75
  • PDF
Pixelwise Instance Segmentation with a Dynamically Instantiated Network
  • A. Arnab, P. Torr
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
  • 154
  • PDF
Mask R-CNN
  • 5,801
...
1
2
3
4
...