Code Releasing of Recent Work--Derivative Manipulation and IMAE

For source codes, the usage is conditioned on academic use only and kindness to cite our work: Derivative Manipulation and IMAE.
As a young researcher, your interest and star (citation) will mean a lot for me and my collaborators.
For any specific discussion or potential future collaboration, please feel free to contact me.

  1. IMAE for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude’s Variance Matters
  2. Derivative Manipulation for General Example Weighting
  3. Github Pages
  4. Citation
    @article{wang2020proselflc,
      title={ProSelfLC: Progressive Self Label Correction 
      for Training Robust Deep Neural Networks},
      author={Wang, Xinshao and Hua, Yang and Kodirov, Elyor and Robertson, Neil M},
      journal={arXiv preprint arXiv:2005.03788},
      year={2020}
    }
    
    @article{wang2020proselflc,
      title={ProSelfLC: Progressive Self Label Correction 
      for Training Robust Deep Neural Networks},
      author={Wang, Xinshao and Hua, Yang and Kodirov, Elyor and Robertson, Neil M},
      journal={arXiv preprint arXiv:2005.03788},
      year={2020}
    }
    
# #

© 2019-2023. All rights reserved.

Welcome to Xinshao Wang's Personal Website