search

nazmul-karim170 / UNICON

[CVPR'22] Official Implementation of the CVPR 2022 paper "UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning"
MIT License
60 stars 15 forks source link

tabular data/ noisy instances/ new datasets #1

Closed nazaretl closed 2 years ago

nazaretl commented 2 years ago

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

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

Thanks!

nazmul-karim170 commented 2 years ago

It should work on tabular data. You need to change the data loader accordingly. It is possible to identify the indices of clean and noisy samples, just don’t shuffle the data.

Best, Nazmul On Tue, May 10, 2022 at 05:25 nazaretl @.***> wrote:

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

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

Thanks!

— Reply to this email directly, view it on GitHub https://github.com/nazmul-karim170/UNICON-Noisy-Label/issues/1, or unsubscribe https://github.com/notifications/unsubscribe-auth/AF24QPJKR5VXDI2L4MI36LDVJITQ7ANCNFSM5VQ5ZCIQ . You are receiving this because you are subscribed to this thread.Message ID: @.***>

nazaretl commented 2 years ago

may thanks!