Most existing methods for unsupervised domain adaptation (UDA) rely on a shared network to extract domain-invariant features. However, when facing multiple source domains, optimizing such a network involves updating the parameters of the entire network, making it both computationally expensive and challenging, particularly when coupled with min-max objectives. Inspired by recent advances in prompt learning that adapts high-capacity models for downstream tasks in a computationally economic way, we introduce Multi-Prompt Alignment (MPA), a simple yet efficient framework for multi-source UDA. Given a source and target domain pair, MPA first trains an individual prompt to minimize the domain gap through a contrastive loss. Then, MPA denoises the learned prompts through an auto-encoding process and aligns them by maximizing the agreement of all the reconstructed prompts. Moreover, we show that the resulting subspace acquired from the auto-encoding process can easily generalize to a streamlined set of target domains, making our method more efficient for practical usage. Extensive experiments show that MPA achieves state-of-the-art results on three popular datasets with an impressive average accuracy of 54.1% on DomainNet.

翻译：大多数现有的无监督领域自适应（UDA）方法依赖共享网络提取域不变特征。然而，当面对多个源域时，优化此类网络需更新整个网络的参数，这不仅计算成本高昂且极具挑战性，尤其是在结合最小-最大目标函数的情况下。受近期提示学习（一种以计算经济的方式适配高容量模型至下游任务）进展的启发，我们提出多提示对齐（MPA）——一种用于多源UDA的简洁高效框架。给定一对源域与目标域，MPA首先通过对比损失训练个体提示以最小化域差距；随后，通过自编码过程对所学提示进行去噪，并通过最大化所有重构提示的一致性实现对齐。此外，我们证明自编码过程得到的子空间可轻松泛化至简化后的目标域集合，使该方法在实际应用中更具效率。大量实验表明，MPA在三个主流数据集上均达到最优结果，在DomainNet上实现了54.1%的惊人平均准确率。