In semi-supervised domain adaptation (SSDA), a few labeled target samples of each class help the model to transfer knowledge representation from the fully labeled source domain to the target domain. Many existing methods ignore the benefits of making full use of the labeled target samples from multi-level. To make better use of this additional data, we propose a novel Prototype-based Multi-level Learning (ProML) framework to better tap the potential of labeled target samples. To achieve intra-domain adaptation, we first introduce a pseudo-label aggregation based on the intra-domain optimal transport to help the model align the feature distribution of unlabeled target samples and the prototype. At the inter-domain level, we propose a cross-domain alignment loss to help the model use the target prototype for cross-domain knowledge transfer. We further propose a dual consistency based on prototype similarity and linear classifier to promote discriminative learning of compact target feature representation at the batch level. Extensive experiments on three datasets, including DomainNet, VisDA2017, and Office-Home demonstrate that our proposed method achieves state-of-the-art performance in SSDA.

翻译：在半监督域适应（SSDA）中，每个类别少量带标签的目标样本有助于模型将知识表示从完全标注的源域迁移至目标域。现有方法多忽视了从多层级充分利用这些带标签目标样本的益处。为更有效利用这些额外数据，我们提出了一种新颖的基于原型的多层级学习（ProML）框架，以深入挖掘带标签目标样本的潜力。为实现域内适应，我们首先引入基于域内最优传输的伪标签聚合方法，帮助模型对齐未标注目标样本的特征分布与原型。在跨域层级上，我们提出跨域对齐损失函数，帮助模型利用目标原型进行跨域知识迁移。进一步地，我们提出基于原型相似性与线性分类器的双重一致性约束，促进批层级上紧凑目标特征表示的判别性学习。在包含DomainNet、VisDA2017和Office-Home的三个数据集上的大量实验表明，所提方法在SSDA任务中取得了最先进的性能。