Without access to the source data, source-free domain adaptation (SFDA) transfers knowledge from a source-domain trained model to target domains. Recently, SFDA has gained popularity due to the need to protect the data privacy of the source domain, but it suffers from catastrophic forgetting on the source domain due to the lack of data. To systematically investigate the mechanism of catastrophic forgetting, we first reimplement previous SFDA approaches within a unified framework and evaluate them on four benchmarks. We observe that there is a trade-off between adaptation gain and forgetting loss, which motivates us to design a consistency regularization to mitigate forgetting. In particular, we propose a continual source-free domain adaptation approach named CoSDA, which employs a dual-speed optimized teacher-student model pair and is equipped with consistency learning capability. Our experiments demonstrate that CoSDA outperforms state-of-the-art approaches in continuous adaptation. Notably, our CoSDA can also be integrated with other SFDA methods to alleviate forgetting.

翻译：在没有源数据访问权限的情况下，无源域自适应（SFDA）将从源域训练的模型知识迁移到目标域。近年来，因需要保护源域的数据隐私，SFDA受到广泛关注，但由于缺乏数据，它在源域上面临灾难性遗忘问题。为系统研究灾难性遗忘的机制，我们首先在统一框架内重新实现了现有的SFDA方法，并在四个基准数据集上进行了评估。我们发现，自适应增益与遗忘损失之间存在权衡，这促使我们设计一种一致性正则化方法来缓解遗忘。具体而言，我们提出了一种名为CoSDA的持续无源域自适应方法，该方法采用双速优化的师生模型对，并具备一致性学习能力。实验表明，CoSDA在持续自适应场景中优于现有最先进方法。值得注意的是，我们的CoSDA还可与其他SFDA方法集成，以缓解遗忘问题。