Suppose there is a ML network that takes grayscale images as the input. The images that I have are RGB images. So, instead of converting these RGB images to grayscale, I treat each individual colour bands as distinct inputs to the network. that is, instead of feeding RGB image A to the network, I feed the R matrix of A as the first input, followed by the G matrix and then the B matrix. This leads to 3 times more data for the network. Can this be considered as data augmentation (since we are increasing the amount of data)? If yes, what is the name of this data augmentation technique?
Yes, when you use single color channel considered as Data Augmentation. This is known as Color Space Augmentation
Digital image data is usually encoded as a tensor of the dimension (height × width × color channels). Performing augmentations in the color channels space is another strategy that is very practical to implement.
An image can be quickly converted into its representation in one color channel by isolating that matrix and adding 2 zero matrices from the other color channels.