Giters

Newbeeer / L_DMI

Code for NeurIPS 2019 Paper, "L_DMI: An Information-theoretic Noise-robust Loss Function"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

new datasets/ noisy instances

nazaretl opened this issue · comments

commented

Hi,
thanks for sharing your implementation. I have two questions about it:

  1. Is the code tailored to the datasets used in the paper or can one apply it to any data?
  2. Is it possible to identify the noisy instances (return the noisy IDs or the clean set)?

Thanks!

commented

Hi,

Sorry for the huge delay. The code works for general dataset. Our method does not have the capability for idetifying the clean set. However, we prove that training with DMI loss on noisy label is equivalent to vanilla ERM on clean set.