In real-world applications, deep learning models often run in non-stationary environments where the target data distribution continually shifts over time. There have been numerous domain adaptation (DA) methods in both online and offline modes to improve cross-domain adaptation ability. However, these DA methods typically only provide good performance after a long period of adaptation, and perform poorly on new domains before and during adaptation - in what we call the "Unfamiliar Period", especially when domain shifts happen suddenly and significantly. On the other hand, domain generalization (DG) methods have been proposed to improve the model generalization ability on unadapted domains. However, existing DG works are ineffective for continually changing domains due to severe catastrophic forgetting of learned knowledge. To overcome these limitations of DA and DG in handling the Unfamiliar Period during continual domain shift, we propose RaTP, a framework that focuses on improving models' target domain generalization (TDG) capability, while also achieving effective target domain adaptation (TDA) capability right after training on certain domains and forgetting alleviation (FA) capability on past domains. RaTP includes a training-free data augmentation module to prepare data for TDG, a novel pseudo-labeling mechanism to provide reliable supervision for TDA, and a prototype contrastive alignment algorithm to align different domains for achieving TDG, TDA and FA. Extensive experiments on Digits, PACS, and DomainNet demonstrate that RaTP significantly outperforms state-of-the-art works from Continual DA, Source-Free DA, Test-Time/Online DA, Single DG, Multiple DG and Unified DA&DG in TDG, and achieves comparable TDA and FA capabilities.

翻译：在现实应用中，深度学习模型常运行于非平稳环境中，目标数据分布随时间持续变化。已有大量在线和离线模式下的域适应（DA）方法，旨在提升跨域适应能力。然而，这些DA方法通常仅能在长期适应后获得良好性能，在适应前和适应过程中（我们称之为"陌生期"）对新域表现欠佳，尤其是当域发生剧烈突变时。另一方面，域泛化（DG）方法被提出用于提升模型在未适应域上的泛化能力。但现有DG工作因对已学知识的严重灾难性遗忘，难以应对持续变化的域。为克服DA和DG在处理持续域偏移中"陌生期"的局限，我们提出RaTP框架，该框架专注于提升模型的目标域泛化（TDG）能力，同时能在特定域训练后立即实现有效目标域适应（TDA）能力，并对过往域具备遗忘缓解（FA）能力。RaTP包含一个无需训练的数据增强模块用于制备TDG所需数据、一种新型伪标签机制为TDA提供可靠监督，以及一种原型对比对齐算法用于对齐不同域以实现TDG、TDA与FA。在Digits、PACS和DomainNet上的大量实验表明，RaTP在TDG上显著超越持续DA、无源DA、测试/在线DA、单源DG、多源DG及统一DA&DG等领域的最新方法，并达到同等的TDA与FA能力。