Thanks!Very helpful! In AlexNet paper they worked with intensities of the RGB: “Specifically, we perform PCA on the set of RGB pixel values throughout the ImageNet training set. To each training image, we add multiples of the found principal components, with magnitudes proportional to the corresponding eigenvalues times a random variable drawn from a Gaussian with mean zero and standard deviation 0.1”. Did you try this one? I’m working with most of them that you described, but this is something another though looks like Gaussian nose .