fastfcn

FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation

Introduction

Official Repo

Code Snippet

FastFCN (ArXiv'2019)

@article{wu2019fastfcn,
title={Fastfcn: Rethinking dilated convolution in the backbone for semantic segmentation},
author={Wu, Huikai and Zhang, Junge and Huang, Kaiqi and Liang, Kongming and Yu, Yizhou},
journal={arXiv preprint arXiv:1903.11816},
year={2019}
}

Results and models

Cityscapes

Method	Backbone	Crop Size	Lr schd	Mem (GB)	Inf time (fps)	mIoU	mIoU(ms+flip)	config	download
DeepLabV3 + JPU	R-50-D32	512x1024	80000	5.67	2.64	79.12	80.58	config	model | log
DeepLabV3 + JPU (4x4)	R-50-D32	512x1024	80000	9.79	-	79.52	80.91	config	model | log
PSPNet + JPU	R-50-D32	512x1024	80000	5.67	4.40	79.26	80.86	config	model | log
PSPNet + JPU (4x4)	R-50-D32	512x1024	80000	9.94	-	78.76	80.03	config	model | log
EncNet + JPU	R-50-D32	512x1024	80000	8.15	4.77	77.97	79.92	config	model | log
EncNet + JPU (4x4)	R-50-D32	512x1024	80000	15.45	-	78.6	80.25	config	model | log

Note:

• 4x4 means 4 GPUs with 4 samples per GPU in training, default setting is 4 GPUs with 2 samples per GPU in training.
• Results of DeepLabV3 (mIoU: 79.32), PSPNet (mIoU: 78.55) and ENCNet (mIoU: 77.94) can be found in each original repository.