amanupg / moss

Memory Oriented Transfer Learning for Semi-Supervised Image Deraining

Moss

Code for Paper "Memory Oriented Transfer Learning for Semi-Supervised Image Deraining"

Prerequisites

• Python 3
• PyTorch

Models

We provide the model trained on DDN-SIRR dataset in the following links:

• Google Driver
• Jianguo Yun

Run

 CUDA_VISIBLE_DEVICES=0 python test.py --config_file='test.yaml'

Adjust the parameters in 'test.yaml' according to your own settings. Please goto the 'train' folder for the training code.

Citation

If you use our codes, please cite the following paper:

 @inproceedings{huang2021memory,
   title={Memory Oriented Transfer Learning for Semi-Supervised Image Deraining},
   author={Huang, Huaibo and Yu, Aijing and He, Ran},
   booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition},
   pages={7732--7741},
   year={2021},
  }

The released codes are only allowed for non-commercial use.