Skip to content

[ICML'2022] Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network

Notifications You must be signed in to change notification settings

ShuoYang-1998/BLTM

Repository files navigation

ICML 2022 Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network

This is the code for the paper: Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network
Shuo Yang, Erkun Yang, Bo Han, Yang Liu, Min Xu, Gang Niu, Tongliang Liu.

Install requirements.txt

pip install -r requirements.txt

Experiments

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{yang2022bltm,
  title={Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network},
  author={Yang, Shuo and Yang, Erkun and Han, Bo and Liu, Yang and Xu, Min and Niu, Gang and Liu, Tongliang},
  booktitle={ICML},
  year={2022}
}

About

[ICML'2022] Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages