Semi-supervised learning (SSL) has seen great strides when labeled data is scarce but unlabeled data is abundant. Critically, most recent work assume that such unlabeled data is drawn from the same distribution as the labeled data. In this work, we show that state-of-the-art SSL algorithms suffer a degradation in performance in the presence of unlabeled auxiliary data that does not necessarily possess the same class distribution as the labeled set. We term this problem as Auxiliary-SSL and propose AuxMix, an algorithm that leverages self-supervised learning tasks to learn generic features in order to mask auxiliary data that are not semantically similar to the labeled set. We also propose to regularize learning by maximizing the predicted entropy for dissimilar auxiliary samples. We show an improvement of 5% over existing baselines on a ResNet-50 model when trained on CIFAR10 dataset with 4k labeled samples and all unlabeled data is drawn from the Tiny-ImageNet dataset. We report competitive results on several datasets and conduct ablation studies.

本研究提出了一种叫做AuxMix的算法，该算法利用自监督学习任务来学习通用特征，以掩盖那些不同于标记集的语义上不相似的辅助数据，并正则化学习通过预测熵最大化来处理不同数据的不确定性，结果显示该算法相比现有的基线在ResNet-50模型上训练CIFAR10数据集时提高了5％。

AuxMix：半监督学习与无限制未标记数据