mmsegmentation/configs/apcnet

Adaptive Pyramid Context Network for Semantic Segmentation

Introduction

@InProceedings{He_2019_CVPR,
author = {He, Junjun and Deng, Zhongying and Zhou, Lei and Wang, Yali and Qiao, Yu},
title = {Adaptive Pyramid Context Network for Semantic Segmentation},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}

Results and models

Cityscapes

Method	Backbone	Crop Size	Lr schd	Mem (GB)	Inf time (fps)	mIoU	mIoU(ms+flip)	download
APCNet	R-50-D8	512x1024	40000	7.7	3.57	78.02	79.26	model | log
APCNet	R-101-D8	512x1024	40000	11.2	2.15	79.08	80.34	model | log
APCNet	R-50-D8	769x769	40000	8.7	1.52	77.89	79.75	model | log
APCNet	R-101-D8	769x769	40000	12.7	1.03	77.96	79.24	model | log
APCNet	R-50-D8	512x1024	80000	-	-	78.96	79.94	model | log
APCNet	R-101-D8	512x1024	80000	-	-	79.64	80.61	model | log
APCNet	R-50-D8	769x769	80000	-	-	78.79	80.35	model | log
APCNet	R-101-D8	769x769	80000	-	-	78.45	79.91	model | log

ADE20K

Method	Backbone	Crop Size	Lr schd	Mem (GB)	Inf time (fps)	mIoU	mIoU(ms+flip)	download
APCNet	R-50-D8	512x512	80000	10.1	19.61	42.20	43.30	model | log
APCNet	R-101-D8	512x512	80000	13.6	13.10	45.54	46.65	model | log
APCNet	R-50-D8	512x512	160000	-	-	43.40	43.94	model | log
APCNet	R-101-D8	512x512	160000	-	-	45.41	46.63	model | log