论文标题
con $^{2} $ da：通过学习一致和对比的特征表示来简化半监督域的适应
Con$^{2}$DA: Simplifying Semi-supervised Domain Adaptation by Learning Consistent and Contrastive Feature Representations
论文作者
论文摘要
在这项工作中，我们提出了一个简单的框架，这是一个简单的框架，将半监视学习的最新进展扩展到半监督域的适应性（SSDA）问题。我们的框架通过对给定输入进行随机数据转换来生成相关样本对。相关的数据对使用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在相关数据对的样本数据对之间执行一致性。我们表明，这些学习的表示形式对于处理域适应问题中数据分布的差异很有用。我们进行了实验以研究模型的主要组成部分，我们表明（i）学习一致和对比的特征表示对于在不同域中提取良好的判别特征至关重要，而ii）ii）我们的模型受益于强大的增强策略的利益。通过这些发现，我们的方法在SSDA的三个基准数据集中实现了最先进的性能。
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.
