Skip to content

Sample Prior Guided Robust Model Learning to Suppress Noisy Labels

Notifications You must be signed in to change notification settings

bupt-ai-cz/PGDF

Repository files navigation

PGDF visitors

PWC PWC PWC

This repo is the official implementation of our paper "Sample Prior Guided Robust Model Learning to Suppress Noisy Labels ".

Citation

If you use this code for your research, please cite our paper "Sample Prior Guided Robust Model Learning to Suppress Noisy Labels ".

@misc{chen2022sample,
      title={Sample Prior Guided Robust Model Learning to Suppress Noisy Labels}, 
      author={Wenkai Chen and Chuang Zhu and Yi Chen and Mengting Li and Tiejun Huang},
      year={2022},
      eprint={2112.01197},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Training

Take CIFAR-10 with 50% symmetric noise as an example:

First, please modify the data_path in presets.json to indicate the location of your dataset.

Then, run

python train_cifar_getPrior.py --preset c10.50sym

to get the prior knowledge. Related files will be saved in checkpoints/c10/50sym/saved/.

Next, run

python train_cifar.py --preset c10.50sym

for the subsequent training process.

c10 means CIFAR-10, 50sym means 50% symmetric noise.
Similarly, if you want to take experiment on CIFAR-100 with 20% symmetric noise, you can use the command:

python train_cifar_getPrior.py --preset c100.20sym
python train_cifar.py --preset c100.20sym

Contact

Wenkai Chen

Chuang Zhu

If you have any question about the code and data, please contact us directly.

Additional Info

The (basic) semi-supervised learning part of our code is borrow from the official DM-AugDesc implementation.

Since this paper has not yet been published, we only release part of the experimental code. We will release all the experimental codes after this paper is accepted by a conference.

About

Sample Prior Guided Robust Model Learning to Suppress Noisy Labels

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages