Debiased Self-Training for Semi-Supervised Learning. (arXiv:2202.07136v5 [cs.LG] UPDATED)

Deep neural networks achieve remarkable performances on a wide range of tasks
with the aid of large-scale labeled datasets. Yet these datasets are
time-consuming and labor-exhaustive to obtain on realistic tasks. To mitigate
the requirement for labeled data, self-training is widely used in
semi-supervised learning by iteratively assigning pseudo labels to unlabeled
samples. Despite its popularity, self-training is well-believed to be
unreliable and often leads to training instability. Our experimental studies
further reveal that the bias in semi-supervised learning arises …

arxiv self-training semi-supervised semi-supervised learning supervised learning training