论文标题
半监督域适应的多层次一致性学习
Multi-level Consistency Learning for Semi-supervised Domain Adaptation
论文作者
论文摘要
半监督域的适应性（SSDA）旨在将从完全标记的源域学习的知识应用于几乎没有标记的目标域。在本文中，我们为SSDA提出了一个多级一致性学习（MCL）框架。具体而言，我们的MCL将目标域样本的不同视图的一致性定于三个级别：（i）在域间层面，我们使用基于原型的最佳传输方法来牢固，准确地对齐源和目标域，该方法利用了目标样品的不同视图的优点； （ii）在域内层面上，我们通过提出新型的班级对比聚类损失来促进歧视性和紧凑的目标特征表示。 （iii）在样本级别，我们遵循标准实践，并通过进行基于一致性的自我训练来提高预测准确性。从经验上讲，我们验证了MCL框架对三个流行的SSDA基准的有效性，即Visda2017，域名和办公室家庭数据集，实验结果表明我们的MCL框架可以实现最新的效果。
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.
