半监督图像分类中的挤奶CowMask算法
Milking CowMask for Semi-Supervised Image Classification
摘要:
一致性正则化是一种用于半监督学习的技术,其在具有少量标记数据的情况下支持许多强有力的分类结果。它的工作原理是鼓励学习模型对未标记数据的扰动具有鲁棒性。在这里,我们提出了一种新的基于掩码的增强方法,称为CowMask。使用它来为半监督一致性正则化提供扰动,我们在ImageNet上实现了最先进的结果,具有10%的标记数据,前5个错误为8.76%,前1个错误为26.06%。此外,我们使用的方法比许多替代方法简单得多。我们通过在SVHN、CIFAR-10和CIFAR-100数据集上运行许多小规模实验,进一步研究了CowMask用于半监督学习的行为,在这些实验中,我们获得了与现有技术相竞争的结果,表明CowMask具有广泛的适用性。我们在https://github.com/google-research/google-research/tree/master/milking_cowmask上开源我们的代码
英文摘要:
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
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。