CoSDA：连续无源域自适应
CoSDA: Continual Source-Free Domain Adaptation
AI总结：
针对无源域自适应中的灾难性遗忘问题，本文提出连续无源域自适应方法 CoSDA，通过双速优化的教师-学生模型对和一致性正则化，在四个基准上优于现有方法，并可与其他 SFDA 方法集成。
摘要：
在无法访问源数据的情况下，无源域自适应（SFDA）将知识从在源域上训练的模型迁移到目标域。近年来，由于保护源域数据隐私的需求，SFDA 受到广泛关注，但由于缺乏数据，它在源域上遭受灾难性遗忘。为系统研究灾难性遗忘的机制，我们首先在一个统一框架内重新实现了以往的 SFDA 方法，并在四个基准上对其进行了评估。我们观察到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来缓解遗忘。特别是，我们提出了一种名为 CoSDA 的连续无源域自适应方法，该方法采用双速优化的教师-学生模型对，并具备一致性学习能力。我们的实验表明，CoSDA 在连续自适应中优于最先进的方法。值得注意的是，我们的 CoSDA 还可以与其他 SFDA 方法集成以缓解遗忘。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
