Chances are that in a few years the faces shown to you in advertisements would have been tailored so
you could identify with them and be more receptive to their messages.
This form of cost-effective mass customization is now made possible with the development of new
generative models for computer vision that does not need large image datasets to function. University
of Pittsburgh researchers Christopher Thomas and Adriana Kovasha used machine learning as a way to
train AI systems to automatically generate persuasive content.
Persuasive content in ads could have positive effects when used to encourage buy-in for government
projects such as health initiatives and welfare reform.
Thomas and Kovasha explain their technique in a Techexplore.com article:
In computer vision, autoencoders work by taking an image and learning to represent that image as a
few numbers, Thomas said. Then, a second piece of the model, the decoder, learns to take those
numbers and reproduce the original image from it. You can almost think of it as a form of compression,
in which a large image is represented by a few numbers.“When this type of machine learning model is trained on a large enough dataset, it starts to represent
semantic aspects within the numbers. For instance, in the model developed by Thomas and Kovashka,
one number would control the shape of a face, another shade of the skin, and so on for other semantic
features.The cool part of this is that once we trained the model to represent faces in 100 numbers, if we then
change some of those numbers and decode them, we can change the face, Thomas said. We can thus transform existing faces so that they look the same but have different attributes, such as eyeglasses,smiling or not, etc., just by changing some of the numbers that our model uses to represent them.
