This repo is the official implementation of our paper "Sample Prior Guided Robust Model Learning to Suppress Noisy Labels ".
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}
}
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 c10.50symto get the prior knowledge. Related files will be saved in checkpoints/c10/50sym/saved/.
Next, run
python train_cifar.py --preset c10.50symfor 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 c100.20sympython train_cifar.py --preset c100.20symWenkai Chen
- email: [email protected]
- wechat: cwkyiyi
Chuang Zhu
- email: [email protected]
- homepage: https://teacher.bupt.edu.cn/zhuchuang/zh_CN/index.htm
If you have any question about the code and data, please contact us directly.
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.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent