论文标题
半监督图像分类的挤奶牛奶奶酪
Milking CowMask for Semi-Supervised Image Classification
论文作者
论文摘要
一致性正则化是一种半监督学习的技术，其基础是很少有标签数据的分类结果。它通过鼓励学习的模型来扰动未标记的数据来起作用。在这里，我们提出了一种新型的基于面具的增强方法，称为Cowmask。使用它为半监督一致性正则化提供扰动，我们在Imagenet上获得了最新的Imagenet结果，其标记为10％的数据，前5个误差为8.76％，TOP-1误差为26.06％。此外，我们使用一种比许多替代方案要简单得多的方法这样做。我们通过在SVHN，CIFAR-10和CIFAR-100数据集上运行许多较小的规模实验，进一步研究半监督学习的牛奶行为，在该实验中，我们与最新的状态达到了结果，表明CowMask广泛适用。我们在https://github.com/google-research/google-research/tree/master/master/milking_cowmask上打开代码
Consistency regularization is a technique for semi-supervised learning that underlies a number of strong results for classification with few labeled data. It works by encouraging a learned model to be robust to perturbations on unlabeled data. Here, we present a novel mask-based augmentation method called CowMask. Using it to provide perturbations for semi-supervised consistency regularization, we achieve a state-of-the-art result on ImageNet with 10% labeled data, with a top-5 error of 8.76% and top-1 error of 26.06%. Moreover, we do so with a method that is much simpler than many alternatives. We further investigate the behavior of CowMask for semi-supervised learning by running many smaller scale experiments on the SVHN, CIFAR-10 and CIFAR-100 data sets, where we achieve results competitive with the state of the art, indicating that CowMask is widely applicable. We open source our code at https://github.com/google-research/google-research/tree/master/milking_cowmask
