Context Encoding for Semantic Segmentation

Introduction

@InProceedings{Zhang_2018_CVPR,
author = {Zhang, Hang and Dana, Kristin and Shi, Jianping and Zhang, Zhongyue and Wang, Xiaogang and Tyagi, Ambrish and Agrawal, Amit},
title = {Context Encoding for Semantic Segmentation},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}

Results and models

Cityscapes

Method	Backbone	Crop Size	Lr schd	Mem (GB)	Inf time (fps)	mIoU	mIoU(ms+flip)	config	download
encnet	R-50-D8	512x1024	40000	8.6	4.58	75.67	77.08	config	model \| log
encnet	R-101-D8	512x1024	40000	12.1	2.66	75.81	77.21	config	model \| log
encnet	R-50-D8	769x769	40000	9.8	1.82	76.24	77.85	config	model \| log
encnet	R-101-D8	769x769	40000	13.7	1.26	74.25	76.25	config	model \| log
encnet	R-50-D8	512x1024	80000	-	-	77.94	79.13	config	model \| log
encnet	R-101-D8	512x1024	80000	-	-	78.55	79.47	config	model \| log
encnet	R-50-D8	769x769	80000	-	-	77.44	78.72	config	model \| log
encnet	R-101-D8	769x769	80000	-	-	76.10	76.97	config	model \| log

ADE20K

Method	Backbone	Crop Size	Lr schd	Mem (GB)	Inf time (fps)	mIoU	mIoU(ms+flip)	config	download
encnet	R-50-D8	512x512	80000	10.1	22.81	39.53	41.17	config	model \| log
encnet	R-101-D8	512x512	80000	13.6	14.87	42.11	43.61	config	model \| log
encnet	R-50-D8	512x512	160000	-	-	40.10	41.71	config	model \| log
encnet	R-101-D8	512x512	160000	-	-	42.61	44.01	config	model \| log