Recent state-of-the-art semi-supervised learning (SSL) methods use a
combination of image-based transformations and consistency regularization as
core components. Such methods, however, are limited to simple transformations
such as traditional data augmentation or convex combinations of two images. In
this paper, we propose a novel learned feature-based refinement and
augmentation method that produces a varied set of complex transformations.
Importantly, these transformations also use information from both within-class
and across-class prototypical representations that we extract through
clustering. We use features already computed across iterations by storing them
in a memory bank, obviating the need for significant extra computation. These
transformations, combined with traditional image-based augmentation, are then
used as part of the consistency-based regularization loss. We demonstrate that
our method is comparable to current state of art for smaller datasets (CIFAR-10
and SVHN) while being able to scale up to larger datasets such as CIFAR-100 and
mini-Imagenet where we achieve significant gains over the state of art
(\textit{e.g.,} absolute 17.44\% gain on mini-ImageNet). We further test our
method on DomainNet, demonstrating better robustness to out-of-domain unlabeled
data, and perform rigorous ablations and analysis to validate the method.

本文提出了一种创新的特征提取和扩增方法，利用聚类提取的内部和跨类别原型代表信息，生成各式各样的复杂变换，结合传统图像扩增用于一致性正则化损失，实验验证结果表明在小尺寸数据集上与当前先进技术相当，且可以扩展到更大的数据集，例如 CIFAR-100 和 mini-Imagenet 上取得重大进展，并在 DomainNet 上实现更好的鲁棒性。