NeurIPS‘20: Part-dependent Label Noise: Towards Instance-dependent Label Noise (PyTorch implementation).

This is the code for the paper: Part-dependent Label Noise: Towards Instance-dependent Label Noise
Xiaobo Xia, Tongliang Liu, Bo Han, Nannan Wang, Mingming Gong, Haifeng Liu, Gang Niu, Dacheng Tao, Masashi Sugiyama.

We implement our methods by PyTorch on NVIDIA Tesla V100 GPU. The environment is as bellow:

• Ubuntu 16.04 Desktop
• PyTorch, version = 1.2.0
• CUDA, version = 10.0
• Anaconda3

pip install -r requirements.txt

We verify the effectiveness of the proposed method on synthetic noisy datasets. In this repository, we provide the used datasets (the images and labels have been processed to .npy format). You should put the datasets in the folder “data” when you have downloaded them.
Here is a training example:

python main.py \
    --dataset mnist \
    --noise_rate 0.2 \
    --gpu 0

If you find this code useful in your research, please cite

@inproceedings{xia2020part,
  title={Part-dependent Label Noise: Towards Instance-dependent Label Noise},
  author={Xia, Xiaobo and Liu, Tongliang and Han, Bo and Wang, Nannan and Gong, Mingming and Liu, Haifeng and Niu, Gang and Tao, Dacheng and Sugiyama, Masashi},
  booktitle={NeurIPS},
  year={2020}
}