Source-free unsupervised domain adaptation (SFUDA) aims to obtain high performance in the unlabeled target domain using the pre-trained source model, not the source data. Existing SFUDA methods assign the same importance to all target samples, which is vulnerable to incorrect pseudo-labels. To differentiate between sample importance, in this study, we propose a novel sample-wise confidence score, the Joint Model-Data Structure (JMDS) score for SFUDA. Unlike existing confidence scores that use only one of the source or target domain knowledge, the JMDS score uses both knowledge. We then propose a Confidence score Weighting Adaptation using the JMDS (CoWA-JMDS) framework for SFUDA. CoWA-JMDS consists of the JMDS scores as sample weights and weight Mixup that is our proposed variant of Mixup. Weight Mixup promotes the model make more use of the target domain knowledge. The experimental results show that the JMDS score outperforms the existing confidence scores. Moreover, CoWA-JMDS achieves state-of-the-art performance on various SFUDA scenarios: closed, open, and partial-set scenarios.
翻译:无源、无监督的域适应(SFUDA)旨在利用预先培训的源模型而不是源数据,在未标签的目标领域取得高绩效。现有的SFUDA方法对所有目标样本都给予同等重视,这容易出现不正确的假标签。为了区分抽样重要性,我们在本研究中提出了一个新的样本性信任评分,即SFUDA的模型-数据结构(JMDS)联合评分。与仅使用源或目标领域知识的现有信任评分不同,JMDS评分使用两种知识。然后,我们建议使用JMDS(CWA-JMDS)框架为SFUDA提供信任度评分。 CoWA-JMDS包括JMDS的评分,作为样本权重和重量混合,这是我们提议的混合变式。Weight Mixup促进模型更多地利用目标领域知识。实验结果表明,JMDS的得分比现有信任得分高于现有的评分。此外,COWA-JMDS在各种S假设情景中实现了最佳业绩:封闭式、开放和部分情景。