Source-Free Unsupervised Domain Adaptation (SFUDA) is a challenging task where a model needs to be adapted to a new domain without access to target domain labels or source domain data. The primary difficulty in this task is that the model's predictions may be inaccurate, and using these inaccurate predictions for model adaptation can lead to misleading results. To address this issue, this paper proposes a novel approach that considers multiple prediction hypotheses for each sample and investigates the rationale behind each hypothesis. By consolidating these hypothesis rationales, we identify the most likely correct hypotheses, which we then use as a pseudo-labeled set to support a semi-supervised learning procedure for model adaptation. To achieve the optimal performance, we propose a three-step adaptation process: model pre-adaptation, hypothesis consolidation, and semi-supervised learning. Extensive experimental results demonstrate that our approach achieves state-of-the-art performance in the SFUDA task and can be easily integrated into existing approaches to improve their performance. The codes are available at \url{https://github.com/GANPerf/HCPR}.

翻译：无源无监督领域自适应（SFUDA）是一项具有挑战性的任务，要求模型在无法访问目标域标签或源域数据的情况下适应新领域。该任务的主要困难在于模型的预测可能不准确，而使用这些不准确的预测进行模型自适应会导致误导性结果。为解决这一问题，本文提出一种新颖方法：为每个样本考虑多个预测假设，并探究每个假设背后的推理依据。通过整合这些假设的推理依据，我们识别出最可能正确的假设，并将其作为伪标注集支持半监督学习过程以实现模型自适应。为获得最优性能，我们提出三步自适应流程：模型预适应、假设整合和半监督学习。大量实验结果表明，我们的方法在SFUDA任务中实现了最先进的性能，且可轻松集成到现有方法中提升其表现。代码已开源至 \url{https://github.com/GANPerf/HCPR}。