Panoptic-DeepLab

Bowen Cheng, Maxwell D. Collins, Yukun Zhu, Ting Liu, Thomas S. Huang +2 more
10/10/2019
cs.CVcs.LGeess.IV

Official code: bowenc0221/panoptic-deeplab (614 stars, Apache-2.0, PyTorch, last commit 2023-06-23).

Abstract

We present Panoptic-DeepLab, a bottom-up and single-shot approach for panoptic segmentation. Our Panoptic-DeepLab is conceptually simple and delivers state-of-the-art results. In particular, we adopt the dual-ASPP and dual-decoder structures specific to semantic, and instance segmentation, respectively. The semantic segmentation branch is the same as the typical design of any semantic segmentation model (e.g., DeepLab), while the instance segmentation branch is class-agnostic, involving a simple instance center regression. Our single Panoptic-DeepLab sets the new state-of-art at all three Cityscapes benchmarks, reaching 84.2% mIoU, 39.0% AP, and 65.5% PQ on test set, and advances results on the other challenging Mapillary Vistas.

View on arXivView PDF

Code Implementations(1)

bowenc0221/panoptic-deeplabOfficial100%
PyTorchApache-2.0

This is Pytorch re-implementation of our CVPR 2020 paper "Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation" (https://arxiv.org/abs/1911.10194)

614116PythonJun 9, 20203 years agoApache-2.0
bottom-upcityscapescvpr2020deeplabdetectron2+5 more

Similar Papers

Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation

96% match1 repo6142019

Panoptic Feature Pyramid Networks

90% match1 repo34.9k2019

Ensembling Instance and Semantic Segmentation for Panoptic Segmentation

90% match2023

OneFormer3D: One Transformer for Unified Point Cloud Segmentation

88% match1 repo6172023

RT-K-Net: Revisiting K-Net for Real-Time Panoptic Segmentation

88% match1 repo152023

EOV-Seg: Efficient Open-Vocabulary Panoptic Segmentation

87% match1 repo402024

Cite this paper

@article{cheng2019panopticdeeplab,
  title  = {Panoptic-DeepLab},
  author = {Bowen Cheng and Maxwell D. Collins and Yukun Zhu and Ting Liu and Thomas S. Huang and Hartwig Adam and Liang-Chieh Chen},
  year   = {2019},
  eprint = {1910.04751},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1910.04751}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1910.04751.svg)](https://codeofpaper.com/paper/1910.04751)

Discussion