通过特征精炼提升无监督域适应性能，增强模型对分布偏移的鲁棒性。
Domain Adaptation via Feature Refinement
- 利用目标域无标签数据优化批归一化统计量，结合源域模型特征蒸馏与假设迁移
- 在多个带噪声数据集上优于现有方法，如CIFAR10-C和PatchCamelyon-C上准确率显著提升
- 适合关注模型泛化能力与鲁棒性的研究者，尤其适用于无标注目标域场景
我们提出一种名为特征精炼的无监督域适应框架（DAFR2），用于应对分布偏移问题。该方法协同整合三个关键组件：利用无标签目标数据调整批量归一化统计量、从源域训练模型中进行特征蒸馏以及假设迁移。通过在统计与表征层面对齐特征分布，DAFR2构建出鲁棒且域不变的特征空间，在无需目标标签、复杂架构或复杂训练目标的情况下实现跨相似域的良好泛化。在包含CIFAR10-C、CIFAR100-C、MNIST-C和PatchCamelyon-C在内的基准数据集上进行的大量实验表明，该算法在抗干扰能力方面优于先前方法。理论与实证分析进一步揭示，本方法实现了更好的特征对齐，提升了域间互信息，并降低了对输入扰动的敏感性。
原文摘要 · Abstract (English)
We propose Domain Adaptation via Feature Refinement (DAFR2), a simple yet effective framework for unsupervised domain adaptation under distribution shift. The proposed method synergistically combines three key components: adaptation of Batch Normalization statistics using unlabeled target data, feature distillation from a source-trained model and hypothesis transfer. By aligning feature distributions at the statistical and representational levels, DAFR2 produces robust and domain-invariant feature spaces that generalize across similar domains without requiring target labels, complex architectures or sophisticated training objectives. Extensive experiments on benchmark datasets, including CIFAR10-C, CIFAR100-C, MNIST-C and PatchCamelyon-C, demonstrate that the proposed algorithm outperforms prior methods in robustness to corruption. Theoretical and empirical analyses further reveal that our method achieves improved feature alignment, increased mutual information between the domains and reduced sensitivity to input perturbations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。