Deep Critical Learning. Implementation of ProSelfLC, IMAE, DM, etc.
Here are related papers on the fitting and generalization of deep learning:
@article{wang2022proselflc,
title={ProSelfLC: Progressive Self Label Correction Towards A Low-Temperature Entropy State},
author={Wang, Xinshao and Hua, Yang and Kodirov, Elyor and Mukherjee, Sankha Subhra and Clifton, David A and Robertson, Neil M},
journal={bioRxiv},
year={2022}
}
@inproceddings{wang2021proselflc,
title={ {ProSelfLC}: Progressive Self Label Correction
for Training Robust Deep Neural Networks},
author={Wang, Xinshao and Hua, Yang and Kodirov, Elyor and Clifton, David A and Robertson, Neil M},
booktitle={CVPR},
year={2021}
}
@phdthesis{wang2020example,
title={Example weighting for deep representation learning},
author={Wang, Xinshao},
year={2020},
school={Queen's University Belfast}
}
@article{wang2019derivative,
title={Derivative Manipulation for General Example Weighting},
author={Wang, Xinshao and Kodirov, Elyor and Hua, Yang and Robertson, Neil},
journal={arXiv preprint arXiv:1905.11233},
year={2019}
}
@article{wang2019imae,
title={{IMAE} for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude’s Variance Matters},
author={Wang, Xinshao and Hua, Yang and Kodirov, Elyor and Robertson, Neil M},
journal={arXiv preprint arXiv:1903.12141},
year={2019}
}
Proselflc
: Training the shufflenetv2
on cifar-100 with a symmetric noise rate of 40%
Proselflc
: Training the resnet18
on cifar-100 with a symmetric noise rate of 40%
Label smoothing
: Training the shufflenetv2
on cifar-100 with a symmetric noise rate of 40%
Proselflc
: Training the bert transformers
on deeploc dataset with unknown labels
export PATH="/home/ubuntu/.local/bin:$PATH"
-> source ~/.bashrcthis repo
this repo
this repo
CUDA_VISIBLE_DEVICES=0 CUBLAS_WORKSPACE_CONFIG=:4096:8 TOKENIZERS_PARALLELISM=false python -W ignore tests/convnets_cifar100/trainer_calibration_vision_cifar100_covnets_proselflc.py
CUDA_VISIBLE_DEVICES=0 CUBLAS_WORKSPACE_CONFIG=:4096:8 TOKENIZERS_PARALLELISM=false python -W ignore tests/protbertbfd_deeploc/MS-with-unknown/test_trainer_2MSwithunknown_proselflc.py
The results are well sinked and organised, e.g.,