Source-free Unsupervised Domain Adaptation (SF-UDA) aims to adapt a well-trained source model to an unlabeled target domain without access to the source data. One key challenge is the lack of source data during domain adaptation. To handle this, we propose to mine the hidden knowledge of the source model and exploit it to generate source avatar prototypes. To this end, we propose a Contrastive Prototype Generation and Adaptation (CPGA) method. CPGA consists of two stages: Prototype generation and Prototype adaptation. Extensive experiments on three UDA benchmark datasets demonstrate the superiority of CPGA. However, existing SF.UDA studies implicitly assume balanced class distributions for both the source and target domains, which hinders their real applications. To address this issue, we study a more practical SF-UDA task, termed imbalance-agnostic SF-UDA, where the class distributions of both the unseen source domain and unlabeled target domain are unknown and could be arbitrarily skewed. This task is much more challenging than vanilla SF-UDA due to the co-occurrence of covariate shifts and unidentified class distribution shifts between the source and target domains. To address this task, we extend CPGA and propose a new Target-aware Contrastive Prototype Generation and Adaptation (T-CPGA) method. Specifically, for better prototype adaptation in the imbalance-agnostic scenario, T-CPGA applies a new pseudo label generation strategy to identify unknown target class distribution and generate accurate pseudo labels, by utilizing the collective intelligence of the source model and an additional contrastive language-image pre-trained model. Meanwhile, we further devise a target label-distribution-aware classifier to adapt the model to the unknown target class distribution. We empirically show that T-CPGA significantly outperforms CPGA and other SF-UDA methods in imbalance-agnostic SF-UDA.

翻译：无监督源域自适应（SF-UDA）旨在无源数据条件下，将预训练的源模型适配至无标签的目标域。其关键挑战在于域适配过程中源数据的缺失。为此，我们提出挖掘源模型的隐式知识并生成源域原型原型。具体而言，我们提出对比原型生成与适配方法（CPGA），该方法包含原型生成与原型适配两个阶段。在三个UDA基准数据集上的大量实验证明了CPGA的优越性。然而，现有SF-UDA研究隐含假设源域与目标域类别分布平衡，这限制了其实际应用。为解决该问题，我们研究了一种更实用的SF-UDA任务，称为分布不感知SF-UDA，其中不可见的源域与无标签的目标域类别分布均未知且可能任意倾斜。由于源域与目标域之间协变量偏移与未识别类别分布偏移的共存，该任务比常规SF-UDA更具挑战性。我们通过扩展CPGA提出新的目标感知对比原型生成与适配方法（T-CPGA）。具体而言，为在分布不感知场景下实现更好的原型适配，T-CPGA采用新型伪标签生成策略，利用源模型与额外对比语言-图像预训练模型的集体智能，识别未知的目标类别分布并生成准确伪标签。同时，我们进一步设计了目标标签分布感知分类器，使模型适配至未知的目标类别分布。实验证明，在分布不感知SF-UDA任务中，T-CPGA显著优于CPGA及其他SF-UDA方法。