History

xieenze 073b02d986 update		2021-06-13 00:32:37 +08:00
..
README.md	update	2021-06-13 00:32:37 +08:00
fpn_r18_512x512_80k_ade20k.py	update	2021-06-13 00:32:37 +08:00
fpn_r50_512x512_80k_ade20k.py	update	2021-06-13 00:32:37 +08:00
fpn_r101_512x512_80k_ade20k.py	update	2021-06-13 00:32:37 +08:00
fpn_x101324d_512x512_80k_ade20k.py	update	2021-06-13 00:32:37 +08:00
fpn_x101644d_512x512_80k_ade20k.py	update	2021-06-13 00:32:37 +08:00

README.md

Panoptic Feature Pyramid Networks

Introduction

[ALGORITHM]

@article{Kirillov_2019,
   title={Panoptic Feature Pyramid Networks},
   ISBN={9781728132938},
   url={http://dx.doi.org/10.1109/CVPR.2019.00656},
   DOI={10.1109/cvpr.2019.00656},
   journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
   publisher={IEEE},
   author={Kirillov, Alexander and Girshick, Ross and He, Kaiming and Dollar, Piotr},
   year={2019},
   month={Jun}
}

Results and models

Cityscapes

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

ADE20K

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