Embracing the artificial
Which of these two images looks best? Which would best train a neural network to segment humans from the background?
One would think Style A would be better. It looks more like a natural image, and therefore should be the better choice.
And yet…
It is actually Style B which works best for training a segmentation network. A technique know as Domain Randomization shows that creating images which look surreal to a human turn out to be better for training a network. …
Adam Schuster
Computer vision engineer with a focus on synthetic datasets for neural networks.
