WarPI
The official PyTorch implemention of our paper "Learning to Rectify for Robust Learning with Noisy Labels".
Run python main.py --corruption_type flip --corruption_prob 0.4 --dataset cifar10 --sample_number 1 --gpuid 0
Cite
If you find the code useful, please consider citing our paper:
@article{SUN2021108467, title = {Learning to Rectify for Robust Learning with Noisy Labels}, author = {Haoliang Sun and Chenhui Guo and Qi Wei and Zhongyi Han and Yilong Yin}, journal = {Pattern Recognition}, pages = {108467}, year = {2021}, issn = {0031-3203}, doi = {https://doi.org/10.1016/j.patcog.2021.108467} }
License
This project is licensed under the terms of the MIT license.