Source-free domain adaptation (SFDA) aims to adapt a source-trained model to an unlabeled target domain without access to the source data. SFDA has attracted growing attention in recent years, where existing approaches focus on self-training that usually includes pseudo-labeling techniques. In this paper, we introduce a novel noise-learning approach tailored to address noise distribution in domain adaptation settings 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, resulting in better prediction accuracy. We demonstrate the effectiveness of our approach when combined with several SFDA methods: SHOT, SHOT++, and AaD. We obtain state-of-the-art results on three domain adaptation datasets: VisDA, DomainNet, and OfficeHome.

翻译：源域无关域适应（SFDA）旨在不依赖源域数据的情况下，将源域训练模型适配至无标签目标域。近年来SFDA备受关注，现有方法主要聚焦于自训练技术，通常包含伪标签策略。本文提出一种新颖的噪声学习框架，专门应对域适应场景中的噪声分布，并实现伪标签的去混淆化。具体而言，我们通过学习伪标签的噪声转移矩阵来捕获各类别的标签污染程度，并挖掘潜在的真实标签分布。噪声转移矩阵的估计有助于更准确的真类后验概率估计，从而提升预测精度。我们证明了该方法与多种SFDA方法（SHOT、SHOT++、AaD）结合时的有效性，并在VisDA、DomainNet、OfficeHome三个域适应数据集上取得了当前最优结果。