fastfcn

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

CityScapes

Segmentor	Pretrain	Backbone	Crop Size	Schedule	Train/Eval Set	mIoU	Download
EncNet	ImageNet-1k-224x224	R-50-D32	512x1024	LR/POLICY/BS/EPOCH: 0.01/poly/8/220	train/val	78.42%	cfg | model | log
PSPNet	ImageNet-1k-224x224	R-50-D32	512x1024	LR/POLICY/BS/EPOCH: 0.01/poly/8/220	train/val	79.36%	cfg | model | log
DeepLabV3	ImageNet-1k-224x224	R-50-D32	512x1024	LR/POLICY/BS/EPOCH: 0.01/poly/8/220	train/val	79.96%	cfg | model | log

More

You can also download the model weights from following sources:

• BaiduNetdisk: https://pan.baidu.com/s/1gD-NJJWOtaHCtB0qHE79rA with access code s757