Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning
Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning
Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active research topic due to its key role on relaxing human supervision. In the context of image classification, recent advances to learn from unlabeled samples are mainly focused on consistency regularization methods that encourage invariant predictions for different …