You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I downloaded the image dataset and found that there are four image directories.
I guess that 'amplifed', 'frameA', and 'frameB' are Y, Xa, and Xb in the paper.
I wonder 'frameC' is X'b or not.
And do you also have the loss term L1(V'b,V'Y) in the code?
I couldn't find the perturbed Y in the dataset.
Best,
The text was updated successfully, but these errors were encountered:
frameC should be the unperturbed version of frameB. So in paper's terminology, frameB is Xb' and frameC is Xb. You can double check how we do the regularization here:
I downloaded the image dataset and found that there are four image directories.
I guess that 'amplifed', 'frameA', and 'frameB' are Y, Xa, and Xb in the paper.
I wonder 'frameC' is X'b or not.
And do you also have the loss term L1(V'b,V'Y) in the code?
I couldn't find the perturbed Y in the dataset.
Best,
The text was updated successfully, but these errors were encountered: