Self Supervized Learning is a Class of Approaches

Self supervised learning is about how do you train on a large collection of examples that did not have to go through human annotation effort. And so it's not that we don't use labelled data, It's that we are using data that is amotated for free. When you have a videa of what happened in the world, you serve half the future, and came for free in the data stream. So you're still training the network to predict a thing, just like normal supervised learning, but you happen to have that thing for free, without human effort.