Recently, Semi-Supervised Learning (SSL) has shown much promise in leveraging unlabeled data while being provided with very few labels. In this paper, we show that ignoring the labels altogether for whole epochs intermittently during training can significantly improve performance in the small sample regime. More specifically, we propose to train a network on two tasks jointly. The primary classification task is exposed to both the unlabeled and the scarcely annotated data, whereas the secondary task seeks to cluster the data without any labels. As opposed to hand-crafted pretext tasks frequently used in self-supervision, our clustering phase utilizes the same classification network and head in an attempt to relax the primary task and propagate the information from the labels without overfitting them. On top of that, the self-supervised technique of classifying image rotations is incorporated during the unsupervised learning phase to stabilize training. We demonstrate our method's efficacy in boosting several state-of-the-art SSL algorithms, significantly improving their results and reducing running time in various standard semi-supervised benchmarks, including 92.6% accuracy on CIFAR-10 and 96.9% on SVHN, using only 4 labels per class in each task. We also notably improve the results in the extreme cases of 1,2 and 3 labels per class, and show that features learned by our model are more meaningful for separating the data.
翻译:最近,半强化学习(SSL)在利用未贴标签的数据方面显示了很大的希望。 在本文中,我们显示,在培训过程中,不时地忽略整个标记,就可以大大改善小型抽样制度的业绩。更具体地说,我们提议在两个任务上联合培训网络。初级分类任务既暴露在未贴标签和极少附加说明的数据中,而次要任务则寻求将数据无任何标签地分组。相对于在自我监督的视觉中经常使用的手工制作的托辞任务,我们的分组阶段利用同样的分类网络和头来试图放松主要任务和从标签中传播信息,而不过度安装这些标签。此外,在未经监督的学习阶段将自我监督的图像旋转技术纳入到稳定培训中。我们展示了我们的方法在提升几个最先进的SSL算模型方面的效率,大大改进了它们的结果,并缩短了各种标准的半监督基准的运行时间,包括每个等级的92.6%的分类网络和从标签中传播信息,而没有过度安装这些标签。 此外,我们每个等级的SFAR-10和最高等级的标签中也明显地改进了我们每类4-10和969%的数据。