In this work, we present Con$^{2}$DA, a simple framework that extends recent advances in semi-supervised learning to the semi-supervised domain adaptation (SSDA) problem. Our framework generates pairs of associated samples by performing stochastic data transformations to a given input. Associated data pairs are mapped to a feature representation space using a feature extractor. We use different loss functions to enforce consistency between the feature representations of associated data pairs of samples. We show that these learned representations are useful to deal with differences in data distributions in the domain adaptation problem. We performed experiments to study the main components of our model and we show that (i) learning of the consistent and contrastive feature representations is crucial to extract good discriminative features across different domains, and ii) our model benefits from the use of strong augmentation policies. With these findings, our method achieves state-of-the-art performances in three benchmark datasets for SSDA.

翻译：在本文中，我们提出了Con$^{2}$DA，一个将半监督学习的最新进展扩展到半监督域适应（SSDA）问题的简单框架。该框架通过对给定输入执行随机数据变换来生成关联样本对。关联数据对通过特征提取器映射到特征表示空间。我们使用不同的损失函数来强制执行关联数据对特征表示之间的一致性。研究表明，这些学习到的表示有助于处理域适应问题中数据分布的差异。我们通过实验分析了模型的主要组成部分，并发现：（i）学习一致性和对比性特征表示对于跨不同域提取良好的判别性特征至关重要；（ii）模型受益于强增强策略的使用。基于这些发现，我们的方法在三个SSDA基准数据集上达到了最先进的性能。