Semi-supervised learning (SSL) is an efficient framework that can train models with both labeled and unlabeled data. However, constrained by the limited number of labels, the learned representations of SSL are ambiguous and not distinguishable for inter-class samples. Moreover, the performance of SSL is also largely dependent on the model initialization. To deal with the drawbacks of SSL, in this paper, we propose a novel end-to-end representation learning method, namely ActiveMatch, which combines SSL with contrastive learning and active learning to fully leverage the limited labels. Starting from a small amount of labeled data with unsupervised contrastive learning as a warm-up, ActiveMatch then combines SSL and supervised contrastive learning, and actively selects the most representative samples for labeling during the training, resulting in better representations towards the classification. Compared with MixMatch and FixMatch, we show that ActiveMatch achieves the state-of-the-art performance, with 89.24 accuracy on CIFAR-10 with 100 collected labels, and 92.20 accuracy with 200 collected labels.

翻译：半监督的学习(SSL)是一个有效的框架,可以用标签和未标签的数据对模型进行培训。然而,由于标签数量有限,SSL的学习表现模糊不清,对于类际抽样来说无法区分。此外,SSL的表现在很大程度上也取决于模型初始化。为了处理SSL的缺点,我们在本文件中提出了一个新的端到端代表学习方法,即主动Match,它将SSL与对比学习和积极学习相结合,以充分利用有限标签。从少量带有未经监督的对比学习的标签数据作为热量开始,主动Match随后结合SSL和受监督的对比学习,在培训期间积极选择最有代表性的标本,从而更好地体现分类。与MixMatch和FixMatch相比,我们表明,积极Match实现了最先进的性能,在CIFAR-10上实现了89.24的精确度,收集了100个标签,而92.20精确度与200个标签采集。