基于预测理据假设整合的无源无监督域适应
Source-Free Unsupervised Domain Adaptation with Hypothesis Consolidation of Prediction Rationale
AI总结：
针对无源无监督域适应中不准确预测导致适配误导的问题，提出基于多预测假设理据整合的三步适配方法，在SFUDA任务上达SOTA性能且易集成。
摘要：
无源无监督域适应（SFUDA）是一项极具挑战性的任务，要求模型在无法获取目标域标签或源域数据的情况下，适配到新的域。该任务的核心难点在于模型的预测结果可能不准确，而使用这些不准确的预测进行模型适配会导致误导性结果。为解决这一问题，本文提出一种新方法，对每个样本考虑多个预测假设，并探究每个假设背后的理据。通过整合这些假设理据，我们识别出最有可能正确的假设，随后将其作为伪标记集，支撑模型适配的半监督学习过程。为实现最优性能，我们提出三步适配流程：模型预适配、假设整合与半监督学习。大量实验结果表明，本文方法在SFUDA任务上达到了当前最优（state-of-the-art）性能，且可轻松集成到现有方法中以提升其性能。代码可在https://github.com/GANPerf/HCPR 获取。
英文摘要：
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}.
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。
