Question in the paper

[meghbhalerao]

Dear Authors,
Thank you for making the paper and code open source. It is very helpful.

With respect to the image above - 2 steps are being done for adversarial learning - one term where the ld and lc are positive and the next point they are negative. Why not use a gradient reversal layer before the perturbation and covariate discriminator instead of the 2 step process, so that the loss can be back-propagated in a single forward and backward pass? Or this is just a design choice? I am just curious.

Am I missing something? Please let me know.

Thank you,
Megh