The code of: Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation, Weide Liu, Xiangfei Kong, Tzu-Yi Hung, Guosheng Lin, [Paper]

If you find the code useful, please consider citing our paper using the following BibTeX entry.

@article{liu2021cross,
  title={Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation},
  author={Liu, Weide and Kong, Xiangfei and Hung, Tzu-Yi and Lin, Guosheng},
  journal={IEEE Transactions on Multimedia},
  year={2021},
  publisher={IEEE}
}
@article{liu2021cross,
  title={Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation},
  author={Liu, Weide and Kong, Xiangfei and Hung, Tzu-Yi and Lin, Guosheng},
  journal={arXiv preprint arXiv:2108.07413},
  year={2021}
}

• Python 3.7, PyTorch 1.1.0, and more in requirements.txt
• PASCAL VOC 2012 devkit and COCO 2014
• NVIDIA GPU with more than 1024MB of memory

pip install -r requirements.txt

• Follow instructions in http://host.robots.ox.ac.uk/pascal/VOC/voc2012/#devkit

• Follow instructions in https://cocodataset.org/#home

python run_sample.py

• You can either mannually edit the file, or specify commandline arguments.

This project is build based on IRN: https://github.com/jiwoon-ahn/irn. Many thanks to their greak work!

• Training code for MS-COCO
• Code refactoring