Description

This is the pytorch implementation of the ICCV 2023 paper "SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels" by Han Yang, Tianyu Wang, Xiaowei Hu and Chi-Wing Fu.

How to Run

1. Install dependencies

   
   # clone project   
   git clone https://github.com/Cralence/SILT.git

create conda environment

cd SILT conda env create -f environment.yaml conda activate silt pip install opencv-python pip install omegaconf==2.3.0

2. Download the additional non-shadow dataset from [here](https://drive.google.com/file/d/1OHDCr0j6qrSYL1iDokY1kjaMcfRPepui/view?usp=drive_link) if needed. Pretrained weights for the backbone encoders
can be downloaded from the table below. Then, set the correct path and whether to use the additional 
dataset in `configs/silt_training_config.yaml`. Note that we use the additional dataset only when training on SBU.

3. Train the model by running:
```bash
python train.py --dataset SBU --backbone PVT-b5

4. Test the model by running:

   python infer.py --dataset SBU --ckpt path_to_weight  

Dataset

Our relabeled SBU test set, as well as the automatically refined SBU training set, can be downloaded from here.

Pretrained Model

Citation

@inproceedings{yang2023silt,
  title={SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels},
  author={Han Yang, Tianyu Wang, Xiaowei Hu, Chi-Wing Fu},
  booktitle={IEEE International Conference on Computer Vision},
  year={2023}
}