Question about intuition of fitting loss to GMM
hxu38691 opened this issue · comments
Hello, I am new to topic about label noise but very interested in your algorithm, I have two questions in mind if you can help provide some insights into
-
Why fitting loss to GMM instead of others, such as dimension reduced learnt representations, have you experimented with other settings?
-
Related to the first question, if using loss as input to GMM, how is the inference done if validation set also contains noisy labels? Can we still separate clean/noisy label without posterior loss?
Thank you
Hi, thanks for your interest!
-
The per-sample loss highly correlates with the correctness of the label and can be modeled with univariate GMM. Dimension reduced representations may not have such an obvious pattern.
-
In inference the label is not given, and only the network is used for prediction.
I just realized samples are clean...
Thanks, I’m closing this.