semi-supervised-learning
Everything on Ground Truth tagged “semi-supervised-learning” — 1 item.
Pseudo-labeling and self-training Lesson
Pseudo-labeling is training a model on labels it produced itself: run a model over unlabeled data, keep the predictions it is confident about, and treat them as ground truth for the next round of training. It works surprisingly well, and it fails in one specific way -- by confidently reinforcing its own mistakes.