CADA-VAE-PyTorch icon indicating copy to clipboard operation
CADA-VAE-PyTorch copied to clipboard

Published 20 hours ago • verified publisher icon edgarschnfld

Ablation study exmperiment

Open GanAndreas opened this issue 4 years ago • 2 comments

Hi, first of all, thank you for your work. It's so great!!!

I want to recreate your ablation study by train the model with only CA-VAE and DA-VAE. I tried to do it by disable the distance loss or cross-reconstruction loss in the total loss, but I can't get the result on your paper. I only get harmonic mean accuracy of 2.18% for CA-VAE and 39.52% for DA-VAE. Can you point out my mistake?

Thank you

GanAndreas avatar Jun 18 '20 12:06 GanAndreas

Hi, it's very much possible that the hyperparameters have to be adjusted for each ablation, especially the early stopping step for the final classifier. That should be done on the validation split (=the split that is not used for the final testing), see here https://github.com/edgarschnfld/CADA-VAE-PyTorch/issues/10.

edgarschnfld avatar Jul 08 '20 13:07 edgarschnfld

Hi,have you got the true ablation result ? can you show me the details ?

angela000 avatar Oct 08 '20 09:10 angela000