Unsupervised Domain Adaptation (UDA), which aims to explore the transferrable features from a well-labeled source domain to a related unlabeled target domain, has been widely progressed. Nevertheless, as one of the mainstream, existing adversarial-based methods neglect to filter the irrelevant semantic knowledge, hindering adaptation performance improvement. Besides, they require an additional domain discriminator that strives extractor to generate confused representations, but discrete designing may cause model collapse. To tackle the above issues, we propose Crucial Semantic Classifier-based Adversarial Learning (CSCAL), which pays more attention to crucial semantic knowledge transferring and leverages the classifier to implicitly play the role of domain discriminator without extra network designing. Specifically, in intra-class-wise alignment, a Paired-Level Discrepancy (PLD) is designed to transfer crucial semantic knowledge. Additionally, based on classifier predictions, a Nuclear Norm-based Discrepancy (NND) is formed that considers inter-class-wise information and improves the adaptation performance. Moreover, CSCAL can be effortlessly merged into different UDA methods as a regularizer and dramatically promote their performance.

翻译：无监督域适应（UDA）旨在将充分标注的源域中的可迁移特征迁移至相关但无标注的目标域，目前已取得广泛进展。然而，作为主流方法之一，现有基于对抗的方法忽视了对无关语义知识的过滤，从而阻碍了适应性能的提升。此外，这类方法需要额外的域判别器来迫使特征提取器生成混淆表征，但这种分离式设计可能导致模型崩溃。为解决上述问题，我们提出基于关键语义分类器的对抗学习（CSCAL），该方法更关注关键语义知识的迁移，并利用分类器隐式地充当域判别器的角色，无需额外网络设计。具体而言，在类内对齐中，我们设计了配对级差异（PLD）来迁移关键语义知识。此外，基于分类器预测，我们构建了核范数差异（NND），该差异考虑类间信息并提升了适应性能。同时，CSCAL可轻松作为正则化器融入不同UDA方法中，并显著提升其性能。