面向可泛化无源域自适应的一致性正则化
Consistency Regularization for Generalizable Source-free Domain Adaptation
AI总结：
针对现有无源域自适应方法易过拟合、泛化性差的问题，提出含采样伪标签选择与全局校准的一致性正则化框架，提升了模型在目标训练及未见测试集上的性能，达当前最优水平。
摘要：
无源域自适应（SFDA）旨在无需访问源数据集的情况下，将训练良好的源模型适配到无标注目标域，因而可应用于多种现实场景。现有SFDA方法仅在目标训练集上评估其适配后的模型，忽略了来自未见但同分布测试集的数据。这一疏忽导致过拟合问题，并限制了模型的泛化能力。本文提出一种一致性正则化框架，以开发更具泛化性的SFDA方法，该方法可同时提升模型在目标训练集和测试集上的性能。我们的方法利用由弱增强图像生成的软伪标签来监督强增强图像，推动模型训练过程并增强适配后模型的泛化能力。为利用更多潜在有用的监督信息，我们提出一种基于采样的伪标签选择策略，将域偏移更严重的样本纳入考量。此外，我们引入了全局导向的校准方法，以利用全局类别分布和特征聚类信息，进一步改善适配过程。大量实验表明，我们的方法在多个SFDA基准上取得了当前最优性能，并且在未见测试数据集上展现出鲁棒性。
英文摘要：
Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset, making it applicable in a variety of real-world scenarios. Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets. This oversight leads to overfitting issues and constrains the model's generalization ability. In this paper, we propose a consistency regularization framework to develop a more generalizable SFDA method, which simultaneously boosts model performance on both target training and testing datasets. Our method leverages soft pseudo-labels generated from weakly augmented images to supervise strongly augmented images, facilitating the model training process and enhancing the generalization ability of the adapted model. To leverage more potentially useful supervision, we present a sampling-based pseudo-label selection strategy, taking samples with severer domain shift into consideration. Moreover, global-oriented calibration methods are introduced to exploit global class distribution and feature cluster information, further improving the adaptation process. Extensive experiments demonstrate our method achieves state-of-the-art performance on several SFDA benchmarks, and exhibits robustness on unseen testing datasets.
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。
