论文标题
元伪标签
Meta Pseudo Labels
论文作者
论文摘要
我们提出了元伪标签，这是一种半监督的学习方法，在Imagenet上获得了90.2％的新最先进的TOP-1准确性，比现有的最先进的时间要好1.6％。像伪标签一样，Meta Pseudo标签具有教师网络，可以在未标记的数据上生成伪标签来教授学生网络。但是，与固定老师的伪标签不同，元伪标签的老师不断地通过标记的数据集中的学生表现的反馈来调整。结果，老师生成了更好的伪标签来教学学生。我们的代码将在https://github.com/google-research/google-research/tree/master/meta_pseudo_labels上找到。
We present Meta Pseudo Labels, a semi-supervised learning method that achieves a new state-of-the-art top-1 accuracy of 90.2% on ImageNet, which is 1.6% better than the existing state-of-the-art. Like Pseudo Labels, Meta Pseudo Labels has a teacher network to generate pseudo labels on unlabeled data to teach a student network. However, unlike Pseudo Labels where the teacher is fixed, the teacher in Meta Pseudo Labels is constantly adapted by the feedback of the student's performance on the labeled dataset. As a result, the teacher generates better pseudo labels to teach the student. Our code will be available at https://github.com/google-research/google-research/tree/master/meta_pseudo_labels.
