In this paper, we introduce a realistic and challenging domain adaptation problem called Universal Semi-supervised Model Adaptation (USMA), which i) requires only a pre-trained source model, ii) allows the source and target domain to have different label sets, i.e., they share a common label set and hold their own private label set, and iii) requires only a few labeled samples in each class of the target domain. To address USMA, we propose a collaborative consistency training framework that regularizes the prediction consistency between two models, i.e., a pre-trained source model and its variant pre-trained with target data only, and combines their complementary strengths to learn a more powerful model. The rationale of our framework stems from the observation that the source model performs better on common categories than the target-only model, while on target-private categories, the target-only model performs better. We also propose a two-perspective, i.e., sample-wise and class-wise, consistency regularization to improve the training. Experimental results demonstrate the effectiveness of our method on several benchmark datasets.

翻译：本文提出一种现实且具有挑战性的域自适应问题——通用半监督模型自适应（USMA），该问题具有以下特点：i) 仅需预训练的源域模型，ii) 允许源域与目标域拥有不同的标签集（即二者共享公共标签集并各自持有私有标签集），iii) 目标域每个类别仅需少量标注样本。为解决USMA问题，我们提出协同一致性训练框架，该框架通过正则化两个模型（即预训练源模型及其仅基于目标数据训练的变体）的预测一致性，融合其互补优势以学习更强大的模型。该框架基于以下观察：源模型在公共类别上表现优于仅用目标数据的模型，而目标私有类别上则相反。我们还提出双视角（样本级与类别级）一致性正则化以优化训练过程。实验结果表明，该方法在多个基准数据集上具有有效性。