FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning. (arXiv:2205.07246v2 [cs.LG] UPDATED)

Pseudo labeling and consistency regularization approaches based on confidence
thresholding have made great progress in semi-supervised learning (SSL).
However, we argue that existing methods might fail to adopt suitable thresholds
since they either use a pre-defined / fixed threshold or an ad-hoc threshold
adjusting scheme, resulting in inferior performance and slow convergence. We
first analyze a motivating example to achieve some intuitions on the
relationship between the desirable threshold and model's learning status. Based
on the analysis, we hence propose …

arxiv learning semi-supervised semi-supervised learning supervised learning thresholding