bhanML / T-Revision

NeurIPS'19: Are Anchor Points Really Indispensable in Label-Noise Learning?

Are Anchor Points Really Indispensable in Label-Noise Learning?

NeurIPS'19: [Are Anchor Points Really Indispensable in Label-Noise Learning? ](PyTorch implementation).

======== Here is an example:

python main.py --dataset cifar10 --noise_rate 0.5

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

@inproceedings{xia2019,
  title={Are Anchor Points Really Indispensable in Label-Noise Learning?},
  author={Xia, Xiaobo and Liu, Tongliang and Wang, Nannan and Han, Bo and Gong, Chen and Niu, Gang and Sugiyama, Masashi},
  booktitle={NeurIPS},
  pages={1--2},
  year={2019}
}