The nature of the Generator is that it is seeded with random inputs and trains so it is able to fool the adversarial classifier. I.e. it never sees the "true" data.
This isn’t completely accurate. The generator sees the training data in the same way supervised learning might, because the discriminator sees the data, and the generator shares gradients with the discriminator.
Your point stands though, that it’s obviously not overfitting, and no scientist would publish a result that was just overfitting face generation.
Your point stands though, that it’s obviously not overfitting, and no scientist would publish a result that was just overfitting face generation.