[Project] [Paper] [arXiv] [Home]

Official implementation of FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation.
A Faster, Stronger and Lighter framework for semantic segmentation, achieving the state-of-the-art performance and more than 3x acceleration.

@inproceedings{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},
  booktitle = {arXiv preprint arXiv:1903.11816},
  year = {2019}
}

Contact: Hui-Kai Wu (huikaiwu@icloud.com)

2020-02-18: FastFCN can now run on every OS with PyTorch>=1.1.0 and Python==3.*.*

• Replace SyncBatchNorm with torch.nn.SyncBatchNorm.
• Employ torch.nn.DistributedDataParallel.
• Replace all C/C++ extensions with torch.autograd.Function extensions (Pure Python).
• Note: Due to the introduction of torch.nn.DistributedDataParallel, the performance (mIoU) is lower than v1.0.0 under the same hyper-parameter configurations [PContext-ResNet50-Encoding: 50.95% v.s. 51.05%]. Pull requests are welcome to address the issue.

1. PyTorch >= 1.1.0 (Note: The code is test in the environment with python=3.6, cuda=9.0)
2. Download FastFCN

   git clone https://github.com/wuhuikai/FastFCN.git
   cd FastFCN
   

3. Install Requirements

   nose
   tqdm
   scipy
   cython
   requests
   

python -m scripts.prepare_pcontext

python -m scripts.prepare_ade20k

Note: EncNet (ResNet-101) is trained with crop_size=576, while EncNet+JPU (ResNet-101) is trained with crop_size=480 for fitting 4 images into a 12G GPU.

Dataset	Input	GT	EncNet	Ours
PContext
ADE20K

Code borrows heavily from PyTorch-Encoding.