Recently, source-free unsupervised domain adaptation (SFUDA) has emerged as a more practical and feasible approach compared to unsupervised domain adaptation (UDA) which assumes that labeled source data are always accessible. However, significant limitations associated with SFUDA approaches are often overlooked, which limits their practicality in real-world applications. These limitations include a lack of principled ways to determine optimal hyperparameters and performance degradation when the unlabeled target data fail to meet certain requirements such as a closed-set and identical label distribution to the source data. All these limitations stem from the fact that SFUDA entirely relies on unlabeled target data. We empirically demonstrate the limitations of existing SFUDA methods in real-world scenarios including out-of-distribution and label distribution shifts in target data, and verify that none of these methods can be safely applied to real-world settings. Based on our experimental results, we claim that fine-tuning a source pretrained model with a few labeled data (e.g., 1- or 3-shot) is a practical and reliable solution to circumvent the limitations of SFUDA. Contrary to common belief, we find that carefully fine-tuned models do not suffer from overfitting even when trained with only a few labeled data, and also show little change in performance due to sampling bias. Our experimental results on various domain adaptation benchmarks demonstrate that the few-shot fine-tuning approach performs comparatively under the standard SFUDA settings, and outperforms comparison methods under realistic scenarios. Our code is available at https://github.com/daintlab/fewshot-SFDA .

翻译：最近，无监督无源领域自适应（SFUDA）作为一种相比无监督领域自适应（UDA）更实用且可行的方案应运而生，后者假设标注源数据始终可用。然而，SFUDA方法常被忽视的显著局限限制了其实用性。这些局限包括缺乏确定最优超参数的原则性方法，以及当未标注目标数据无法满足某些要求（如封闭集和与源数据相同的标签分布）时的性能退化。所有局限均源于SFUDA完全依赖未标注目标数据。我们通过实验证明了现有SFUDA方法在真实场景中的局限，包括目标数据中的分布外偏移和标签分布偏移，并确认这些方法均无法安全应用于实际环境。基于实验结果，我们主张使用少量标注数据（例如1-shot或3-shot）微调源预训练模型，是规避SFUDA局限的实用可靠方案。与普遍认知相反，我们仔细微调的模型即使仅用少量标注数据训练也不会过拟合，且对采样偏差引起的性能变化极小。我们在多种领域自适应基准上的实验结果表明，小样本微调方法在标准SFUDA设置下表现相当，并在真实场景中优于对比方法。我们的代码见https://github.com/daintlab/fewshot-SFDA。