search

vincent-thevenin / Realistic-Neural-Talking-Head-Models

My implementation of Few-Shot Adversarial Learning of Realistic Neural Talking Head Models (Egor Zakharov et al.).
GNU General Public License v3.0
828 stars 195 forks source link

Instance normalization is used only in generator's downsampling #30

Closed nwatab closed 4 years ago

nwatab commented 4 years ago

Seeing current implementation of this repository, discriminator has instance normalization, but it is against architecture on the paper.

According to the paper,

We base our generator network G(yi(t), eˆi; ψ, P) on the image-to-image translation architecture proposed by Johnson et. al. [20], but replace downsampling and upsampling layers with residual blocks similarly to [6] (with batch normalization [16] replaced by instance normalization [38])

ional part of the discriminator V (xi(t), yi(t); θ), we use similar networks, which consist of residual downsampling blocks (same as the ones used in the generator, but without normalization layers)

vincent-thevenin commented 4 years ago

You're correct. Thanks for pointing that out! I'll make the necessary changes.