论文标题
Lidam：具有局部域适应和迭代匹配的半监督学习
LiDAM: Semi-Supervised Learning with Localized Domain Adaptation and Iterative Matching
论文作者
论文摘要
尽管数据很丰富，但数据标记很昂贵。半监督的学习方法将一些标记的样本与大量未标记的数据相结合，以有效地训练模型。本文介绍了我们提出的方法Lidam，这是一种植根于领域适应和自定进度学习的半监督学习方法。 Lidam首先执行局部域移动，以为模型提取更好的域 - 不变特征，从而产生更准确的簇和伪标记。然后，使用一种新型的迭代匹配技术以自定进度的方式将这些伪标签与真实的类标签对齐，该技术基于多数一致性，而不是高信心预测。同时，对最终分类器进行了训练，可以预测地面真相标签，直到收敛为止。 Lidam在CIFAR-100数据集上实现了最先进的性能，使用2500个标签时，效果优于FixMatch（73.50％对71.82％）。
Although data is abundant, data labeling is expensive. Semi-supervised learning methods combine a few labeled samples with a large corpus of unlabeled data to effectively train models. This paper introduces our proposed method LiDAM, a semi-supervised learning approach rooted in both domain adaptation and self-paced learning. LiDAM first performs localized domain shifts to extract better domain-invariant features for the model that results in more accurate clusters and pseudo-labels. These pseudo-labels are then aligned with real class labels in a self-paced fashion using a novel iterative matching technique that is based on majority consistency over high-confidence predictions. Simultaneously, a final classifier is trained to predict ground-truth labels until convergence. LiDAM achieves state-of-the-art performance on the CIFAR-100 dataset, outperforming FixMatch (73.50% vs. 71.82%) when using 2500 labels.
