Because it is very expensive to collect a large number of labeled samples to train deep neural networks in certain fields, semi-supervised learning (SSL) researcher has become increasingly important in recent years. There are many consistency regularization-based methods for solving SSL tasks, such as the \(\Pi \) model and mean teacher. In this paper, we first show through an experiment that the traditional consistency-based methods exist the following two problems: (1) as the size of unlabeled samples increases, the accuracy of these methods increases very slowly, which means they cannot make full use of unlabeled samples. (2) When the number of labeled samples is vary small, the performance of these methods will be very low. Based on these two findings, we propose two methods, metric learning clustering (MLC) and auxiliary fake samples, to alleviate these problems. The proposed methods achieve state-of-the-art results on SSL benchmarks. The error rates are 10.20%, 38.44% and 4.24% for CIFAR-10 with 4000 labels, CIFAR-100 with 10,000 labels and SVHN with 1000 labels by using MLC. For MNIST, the auxiliary fake samples method shows great results in cases with the very few labels.

由于在某些领域收集大量标记样本来训练深度神经网络非常昂贵，因此半监督学习（SSL）研究人员近年来变得越来越重要。有许多基于一致性正则化的解决 SSL 任务的方法，例如\(\Pi \)模范和卑鄙的老师。在本文中，我们首先通过一个实验表明，传统的基于一致性的方法存在以下两个问题：（1）随着未标记样本数量的增加，这些方法的准确率增加非常缓慢，这意味着它们不能充分利用未标记的样本。(2)当标记样本的数量变化很小时，这些方法的性能会非常低。基于这两个发现，我们提出了两种方法，度量学习聚类（MLC）和辅助假样本，以缓解这些问题。所提出的方法在 SSL 基准测试中取得了最先进的结果。使用 MLC 的 CIFAR-10 有 4000 个标签，CIFAR-100 有 10000 个标签，SVHN 有 1000 个标签，错误率分别为 10.20%、38.44% 和 4.24%。对于 MNIST，