Semi-supervised domain adaptation (SSDA) aims to apply knowledge learned from a fully labeled source domain to a scarcely labeled target domain. In this paper, we propose a Multi-level Consistency Learning (MCL) framework for SSDA. Specifically, our MCL regularizes the consistency of different views of target domain samples at three levels: (i) at inter-domain level, we robustly and accurately align the source and target domains using a prototype-based optimal transport method that utilizes the pros and cons of different views of target samples; (ii) at intra-domain level, we facilitate the learning of both discriminative and compact target feature representations by proposing a novel class-wise contrastive clustering loss; (iii) at sample level, we follow standard practice and improve the prediction accuracy by conducting a consistency-based self-training. Empirically, we verified the effectiveness of our MCL framework on three popular SSDA benchmarks, i.e., VisDA2017, DomainNet, and Office-Home datasets, and the experimental results demonstrate that our MCL framework achieves the state-of-the-art performance.

翻译：半监督的域适应(SCDA)旨在将从一个完全标签的源域学到的知识应用到一个标记很少的目标域;在本文件中,我们提议为SDA建立一个多层次协调学习(MCL)框架。具体地说,我们的MCL将目标域样本不同观点的一致性规范在三个层次:(一) 在跨部一级,我们使用利用目标样品不同观点的利弊的原型最佳运输方法,对源域和目标域进行强有力和准确的对齐;(二) 在内部一级,我们通过提出新型的类别对比性分组损失,促进了解歧视性和紧凑的目标特征表现;(三) 在抽样一级,我们遵循标准做法,通过进行基于一致性的自我培训,提高预测准确性。我们生动地核实了我们的MCL框架在三个流行的SDA基准上的有效性,即VisDA2017、DomainNet和Offa-Home数据集,以及实验结果显示我们的MCL框架实现了状态。