Skip to content

Latest commit

 

History

History
51 lines (34 loc) · 6.31 KB

README.md

File metadata and controls

51 lines (34 loc) · 6.31 KB
Raw

Semantic FPN

Panoptic Feature Pyramid Networks

Introduction

Official Repo

Code Snippet

Abstract

The recently introduced panoptic segmentation task has renewed our community's interest in unifying the tasks of instance segmentation (for thing classes) and semantic segmentation (for stuff classes). However, current state-of-the-art methods for this joint task use separate and dissimilar networks for instance and semantic segmentation, without performing any shared computation. In this work, we aim to unify these methods at the architectural level, designing a single network for both tasks. Our approach is to endow Mask R-CNN, a popular instance segmentation method, with a semantic segmentation branch using a shared Feature Pyramid Network (FPN) backbone. Surprisingly, this simple baseline not only remains effective for instance segmentation, but also yields a lightweight, top-performing method for semantic segmentation. In this work, we perform a detailed study of this minimally extended version of Mask R-CNN with FPN, which we refer to as Panoptic FPN, and show it is a robust and accurate baseline for both tasks. Given its effectiveness and conceptual simplicity, we hope our method can serve as a strong baseline and aid future research in panoptic segmentation.

Results and models

Cityscapes

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) Device mIoU mIoU(ms+flip) config download
FPN R-50 512x1024 80000 2.8 13.54 V100 74.52 76.08 config model | log
FPN R-101 512x1024 80000 3.9 10.29 V100 75.80 77.40 config model | log

ADE20K

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) Device mIoU mIoU(ms+flip) config download
FPN R-50 512x512 160000 4.9 55.77 V100 37.49 39.09 config model | log
FPN R-101 512x512 160000 5.9 40.58 V100 39.35 40.72 config model | log

Citation

@inproceedings{kirillov2019panoptic,
  title={Panoptic feature pyramid networks},
  author={Kirillov, Alexander and Girshick, Ross and He, Kaiming and Doll{\'a}r, Piotr},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={6399--6408},
  year={2019}
}