https://towardsdatascience.com/self-supervised-pre-training-self-training-which-one-to-use-8c796be3779e (Self-)Supervised Pre-training? Self-training? Which one to use? What are the current state of the art in self-supervised pre-training? Do we really need pre-training? How about self-training? towardsdatascience.com algorithm 이 pseudo-label 을 스스로 만들고( pseudo-label : 어떤 task 에 대해 ture 인 label )..