This paper strives for domain generalization, where models are trained exclusively on source domains before being deployed at unseen target domains. We follow the strict separation of source training and target testing but exploit the value of the unlabeled target data itself during inference. We make three contributions. First, we propose probabilistic pseudo-labeling of target samples to generalize the source-trained model to the target domain at test time. We formulate the generalization at test time as a variational inference problem by modeling pseudo labels as distributions to consider the uncertainty during generalization and alleviate the misleading signal of inaccurate pseudo labels. Second, we learn variational neighbor labels that incorporate the information of neighboring target samples to generate more robust pseudo labels. Third, to learn the ability to incorporate more representative target information and generate more precise and robust variational neighbor labels, we introduce a meta-generalization stage during training to simulate the generalization procedure. Experiments on six widely-used datasets demonstrate the benefits, abilities, and effectiveness of our proposal.

翻译：本文致力于解决域泛化问题，即模型在源域上训练后直接部署于未见过的目标域。我们遵循源域训练与目标域测试严格分离的原则，但在推理阶段利用未标记目标数据本身的价值。本文做出三项贡献：第一，提出目标样本的概率伪标记方法，在测试时扩展源域训练模型至目标域。通过将伪标签建模为分布以考虑泛化过程中的不确定性，并缓解不准确伪标签的误导信号。第二，学习融入邻近目标样本信息的变分邻域标签，生成更鲁棒的伪标签。第三，为训练出能够融入更具代表性的目标信息并生成更精确稳健的变分邻域标签的能力，我们在训练阶段引入元泛化阶段以模拟泛化过程。在六个广泛使用的数据集上的实验证明了本方法的优势、能力与有效性。