Context-Integrated and Feature-Refined Network for Lightweight Object Parsing.
Bin Jiang, Wenxuan Tu, Chao Yang, Junsong Yuan.
IEEE Transactions on Image Processing, 29: 5079-5093, 2020.
DOI: 10.1109/TIP.2020.2978583.
All rights reserved. Licensed under the Apache License 2.0.
The code is released for academic research use only. For commercial use, please contact [twx@hnu.edu.cn].
Clone this repo.
git clone https://github.com/WxTu/CIFReNet.git- Windows or Linux
- Python3
- Pytorch(0.3+)
- Numpy
- Torchvision
- Matplotlib
We use Cityscapes, Camvid and Helen datasets. To train a model on these datasets, download datasets from official websites.
Our backbone network is pre-trained on the ImageNet dataset provided by F. Li et al. You can download publically available pre-trained MobileNet v2 from this website.
data/Dataset.py: processes the dataset before passing to the network.model/CIFReNet.py: defines the architecture of the whole model.model/Backbone.py: defines the encoder.model/Layers.py: defines the DSP, MCIM, and others.utils/Config.py: defines some hyper-parameters.utils/Process.py: defines the process of data pretreatment.utils/Utils.py: defines the loss, optimization, metrics, and others.utils/Visualization.py: defines the data visualization.Train.py: the entry point for training and validation.Test.py: the entry point for testing.
Any discussions or concerns are welcomed!
If you use this code for your research, please cite our papers.
@article{Jiang2020Context,
title={Context-Integrated and Feature-Refined Network for Lightweight Object Parsing},
author={Bin Jiang and Wenxuan Tu and Chao Yang and Junsong Yuan},
journal={IEEE Transactions on Image Processing},
volume={29},
pages={5079-5093},
year={2020}
}
https://github.com/ansleliu/LightNet
https://github.com/meetshah1995/pytorch-semseg
https://github.com/zijundeng/pytorch-semantic-segmentation
https://github.com/Tramac/awesome-semantic-segmentation-pytorch