In this paper, we address unsupervised domain adaptation under noisy environments, which is more challenging and practical than traditional domain adaptation. In this scenario, the model is prone to overfitting noisy labels, resulting in a more pronounced domain shift and a notable decline in the overall model performance. Previous methods employed prototype methods for domain adaptation on robust feature spaces. However, these approaches struggle to effectively classify classes with similar features under noisy environments. To address this issue, we propose a new method to detect and correct confusing class pair. We first divide classes into easy and hard classes based on the small loss criterion. We then leverage the top-2 predictions for each sample after aligning the source and target domain to find the confusing pair in the hard classes. We apply label correction to the noisy samples within the confusing pair. With the proposed label correction method, we can train our model with more accurate labels. Extensive experiments confirm the effectiveness of our method and demonstrate its favorable performance compared with existing state-of-the-art methods. Our codes are publicly available at https://github.com/Hehxcf/CPC/.

翻译：本文研究了噪声环境下的无监督域适应问题，该问题比传统域适应更具挑战性和实用性。在此场景中，模型容易过拟合噪声标签，导致域偏移更加显著，整体模型性能显著下降。以往方法采用原型方法在鲁棒特征空间中进行域适应，但这些方法难以在噪声环境下有效分类具有相似特征的类别。为解决此问题，我们提出了一种检测并校正混淆类别对的新方法。首先，基于小损失准则将类别分为简单类和困难类；然后，在源域与目标域对齐后，利用每个样本的前两个预测结果找出困难类中的混淆类别对，并对混淆类别对中的噪声样本进行标签校正。通过所提出的标签校正方法，我们能够使用更准确的标签训练模型。大量实验验证了该方法的有效性，并表明其相较于现有最优方法具有更优性能。我们的代码公开于 https://github.com/Hehxcf/CPC/。