I am trying to find out a paper that mentioned that in a conditional setting, generative adversarial networks overlook the sampled noise. Please let me know if this is not the right place or way to ask this question.
I came across this paper "Image-to-Image Translation with Conditional Adversarial Networks", but the way how the noise is added is not described in the paper.
Past conditional GANs have acknowledged this and provided Gaussian noise z as an input to the generator, in addition to x (e.g., ). In initial experiments, we did not find this strategy effective – the generator simply learned to ignore the noise – which is consistent with Mathieu et al. .