Source-free domain adaptation (SFDA) aims to transfer knowledge learned from
a source domain to an unlabeled target domain, where the source data is
unavailable during adaptation. Existing approaches for SFDA focus on
self-training usually including well-established entropy minimization and
pseudo-labeling techniques. Recent work suggested a co-learning strategy to
improve the quality of the generated target pseudo-labels using robust
pretrained networks such as Swin-B. However, since the generated pseudo-labels
depend on the source model, they may be noisy due to domain shift. In this
paper, we view SFDA from the perspective of label noise learning and learn to
de-confuse the pseudo-labels. More specifically, we learn a noise transition
matrix of the pseudo-labels to capture the label corruption of each class and
learn the underlying true label distribution. Estimating the noise transition
matrix enables a better true class-posterior estimation results with better
prediction accuracy. We demonstrate the effectiveness of our approach applied
with several SFDA methods: SHOT, SHOT++, and AaD. We obtain state-of-the-art
results on three domain adaptation datasets: VisDA, DomainNet, and OfficeHome.

该研究针对无源领域自适应（SFDA），提出了一种通过学习噪声转移矩阵和准确预测的方法，改进了基于伪标签的 SFDA 方法，获得了在 VisDA、DomainNet 和 OfficeHome 三个领域自适应数据集上的最新成果。