Semi-supervised learning (SSL) algorithm is a setup built upon a realistic assumption that access to a large amount of labeled data is tough. In this study, we present a generalized framework, named SCAR, standing for Selecting Clean samples with Adversarial Robustness, for improving the performance of recent SSL algorithms. By adversarially attacking pre-trained models with semi-supervision, our framework shows substantial advances in classifying images. We introduce how adversarial attacks successfully select high-confident unlabeled data to be labeled with current predictions. On CIFAR10, three recent SSL algorithms with SCAR result in significantly improved image classification.

翻译：半监督学习（SSL）算法基于一个现实假设，即获取大量标注数据较为困难。本研究提出一个通用框架，名为SCAR（Selecting Clean samples with Adversarial Robustness，对抗鲁棒性洁净样本选择），旨在提升现有SSL算法的性能。通过利用半监督机制对预训练模型进行对抗攻击，该框架在图像分类任务中展现出显著进步。我们介绍了对抗攻击如何成功筛选出高置信度的未标注数据，并为其赋予当前预测标签。在CIFAR10数据集上，结合SCAR的三种最新SSL算法在图像分类性能上均取得了显著提升。