Adaptive Pyramid Context Network for Semantic Segmentation (APCNet CVPR’2019)

Introduction

Official implementation of Adaptive Pyramid Context Network for Semantic Segmentation (Paper).

🔥

🔥
APCNet is on MMsegmentation.
🔥

🔥

@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}
}

Overview

Framework

image

Results and models

Cityscapes

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) mIoU mIoU(ms+flip) config download
APCNet R-50-D8 512×1024 40000 7.7 3.57 78.02 79.26 config model | log
APCNet R-101-D8 512×1024 40000 11.2 2.15 79.08 80.34 config model | log
APCNet R-50-D8 769×769 40000 8.7 1.52 77.89 79.75 config model | log
APCNet R-101-D8 769×769 40000 12.7 1.03 77.96 79.24 config model | log
APCNet R-50-D8 512×1024 80000 78.96 79.94 config model | log
APCNet R-101-D8 512×1024 80000 79.64 80.61 config model | log
APCNet R-50-D8 769×769 80000 78.79 80.35 config model | log
APCNet R-101-D8 769×769 80000 78.45 79.91 config model | log

ADE20K

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

GitHub

https://github.com/Junjun2016/APCNet