ConMatch: Semi-Supervised Learning with Confidence-Guided Consistency Regularization. (arXiv:2208.08631v2 [cs.CV] UPDATED)

We present a novel semi-supervised learning framework that intelligently
leverages the consistency regularization between the model's predictions from
two strongly-augmented views of an image, weighted by a confidence of
pseudo-label, dubbed ConMatch. While the latest semi-supervised learning
methods use weakly- and strongly-augmented views of an image to define a
directional consistency loss, how to define such direction for the consistency
regularization between two strongly-augmented views remains unexplored. To
account for this, we present novel confidence measures for pseudo-labels from
strongly-augmented …

arxiv confidence regularization semi-supervised semi-supervised learning supervised learning