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 views by means of weakly-augmented view as an anchor in non-parametric and parametric approaches. Especially, in parametric approach, we present, for the first time, to learn the confidence of pseudo-label within the networks, which is learned with backbone model in an end-to-end manner. In addition, we also present a stage-wise training to boost the convergence of training. When incorporated in existing semi-supervised learners, ConMatch consistently boosts the performance. We conduct experiments to demonstrate the effectiveness of our ConMatch over the latest methods and provide extensive ablation studies. Code has been made publicly available at https://github.com/JiwonCocoder/ConMatch.

本文介绍了一种名为ConMatch的新型半监督学习框架，它在图像的两个强大的增强视图的模型预测之间智能地利用一致性正则化，权重由伪标签的置信度确定。该方法通过弱增强视图作为锚点，提出了新的伪标签置信度度量方法，包括非参数方法和参数方法。特别是，在参数方法中，我们首次提出在网络内学习伪标签置信度，可以端到端地与骨干模型一起训练。在现有的半监督学习中加入ConMatch可以持续提高性能，本文通过实验和大量的消融研究证明了ConMatch的有效性。

ConMatch: 带置信度引导的连贯性正则化半监督学习