Semi-Supervised Domain Adaptation (SSDA) leverages knowledge from a fully labeled source domain to classify data in a partially labeled target domain. Due to the limited number of labeled samples in the target domain, there can be intrinsic similarity of classes in the feature space, which may result in biased predictions, even when the model is trained on a balanced dataset. To overcome this limitation, we introduce a multi-view consistency framework, which includes two views for training strongly augmented data. One is a debiasing strategy for correcting class-wise prediction probabilities according to the prediction performance of the model. The other involves leveraging pseudo-negative labels derived from the model predictions. Furthermore, we introduce a cross-domain affinity learning aimed at aligning features of the same class across different domains, thereby enhancing overall performance. Experimental results demonstrate that our method outperforms the competing methods on two standard domain adaptation datasets, DomainNet and Office-Home. Combining unsupervised domain adaptation and semi-supervised learning offers indispensable contributions to the industrial sector by enhancing model adaptability, reducing annotation costs, and improving performance.

翻译：半监督域自适应（SSDA）利用来自完全标记源域的知识对部分标记目标域中的数据进行分类。由于目标域中标记样本数量有限，特征空间中可能存在类别的内在相似性，这可能导致预测偏差，即使模型是在平衡数据集上训练的。为克服这一限制，我们提出了一种多视角一致性框架，该框架包含两个用于训练强增强数据的视角。其一是去偏策略，根据模型的预测性能校正类别预测概率；其二是利用从模型预测中衍生的伪负标签。此外，我们引入了跨域亲和性学习，旨在对齐不同域中同一类别的特征，从而提升整体性能。实验结果表明，我们的方法在两个标准域自适应数据集（DomainNet和Office-Home）上优于现有竞争方法。结合无监督域自适应与半监督学习，通过增强模型适应性、降低标注成本并提升性能，为工业领域提供了不可或缺的贡献。