SCoDA：自监督持续领域自适应
SCoDA: Self-supervised Continual Domain Adaptation
AI总结：
提出SCoDA框架，通过自监督预训练初始化和几何流形对齐原则，结合实例级特征匹配与空间相似度损失及EMA更新，有效解决无源域自适应中的几何信息丢失与灾难性遗忘问题。
摘要：
Source-Free Domain Adaptation (SFDA) 旨在解决在无法访问源域数据的情况下，将模型自适应到目标域的挑战。现有方法通常从全监督预训练的源模型出发，通过对齐实例级特征来蒸馏知识。然而，这些依赖L2归一化特征向量余弦相似度的方法，无意中丢弃了关于源模型潜在流形的关键几何信息。我们提出了Self-supervised Continual Domain Adaptation (SCoDA) 来解决这些局限性。我们对标准做法进行了两项关键改进：首先，通过使用完全通过自监督 (SSL) 预训练的教师模型初始化所提框架，避免了对监督预训练的依赖。其次，我们将几何流形对齐原则应用于SFDA设置。学生模型通过结合实例级特征匹配与Space Similarity Loss的复合目标进行训练。为对抗灾难性遗忘，教师模型的参数通过学生参数的Exponential Moving Average (EMA) 进行更新。在基准数据集上的大量实验表明，SCoDA显著优于现有最先进的SFDA方法。
英文摘要：
Source-Free Domain Adaptation (SFDA) addresses the challenge of adapting a model to a target domain without access to the data of the source domain. Prevailing methods typically start with a source model pre-trained with full supervision and distill the knowledge by aligning instance-level features. However, these approaches, relying on cosine similarity over L2-normalized feature vectors, inadvertently discard crucial geometric information about the latent manifold of the source model. We introduce Self-supervised Continual Domain Adaptation (SCoDA) to address these limitations. We make two key departures from standard practice: first, we avoid the reliance on supervised pre-training by initializing the proposed framework with a teacher model pre-trained entirely via self-supervision (SSL). Second, we adapt the principle of geometric manifold alignment to the SFDA setting. The student is trained with a composite objective combining instance-level feature matching with a Space Similarity Loss. To combat catastrophic forgetting, the teacher's parameters are updated via an Exponential Moving Average (EMA) of the student's parameters. Extensive experiments on benchmark datasets demonstrate that SCoDA significantly outperforms state-of-the-art SFDA methods.
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。
