Thank you for this implementation. It is my understanding that some contrastive frameworks build upon entropy maximization which leads to inapplicability in the contexts of imbalanced datasets. I don't see the direct connection between the ProtoNCE loss and the entropy so I was wondering, does this method support imbalanced datasets?
Hi,
Thank you for this implementation. It is my understanding that some contrastive frameworks build upon entropy maximization which leads to inapplicability in the contexts of imbalanced datasets. I don't see the direct connection between the ProtoNCE loss and the entropy so I was wondering, does this method support imbalanced datasets?
Thanks