Model calibration + confidence learning? #1035
Unanswered
andreimargeloiu
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I couldn't find any discussions on whether it is necessary or helpful to perform model calibration when identifying noisy labels in confidence learning (CL). CL utilizes the model's probabilities in combination with ranking, so it seems intuitive that a calibrated model might improve the detection of noisy labels.
Does anyone have insights on this topic?
Beta Was this translation helpful? Give feedback.
All reactions