通过主动采样与对抗学习，提升无源域自适应的泛化能力
A3: Active Adversarial Alignment for Source-Free Domain Adaptation
- 利用主动学习函数筛选有信息量且多样化的目标数据
- 结合对抗损失与一致性正则，实现无源数据下的分布对齐
- 适合解决标注源数据不可用时的模型迁移问题
无监督域自适应（UDA）旨在将带标签的源域知识迁移到无标签的目标域。近期研究聚焦于无源域自适应（source-free UDA），即仅能访问目标数据。这极具挑战性，因模型依赖噪声伪标签，且难以应对分布偏移。本文提出主动对抗对齐（A3），一种融合自监督学习、对抗训练与主动学习的新框架，用于鲁棒的无源域自适应。A3通过采集函数主动选择具有信息量且多样化的数据进行训练；利用对抗损失和一致性正则化调整模型，实现无需源数据访问的分布对齐。A3通过主动学习与对抗学习的协同整合，有效实现域对齐并降低噪声影响。
原文摘要 · Abstract (English)
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Recent works have focused on source-free UDA, where only target data is available. This is challenging as models rely on noisy pseudo-labels and struggle with distribution shifts. We propose Active Adversarial Alignment (A3), a novel framework combining self-supervised learning, adversarial training, and active learning for robust source-free UDA. A3 actively samples informative and diverse data using an acquisition function for training. It adapts models via adversarial losses and consistency regularization, aligning distributions without source data access. A3 advances source-free UDA through its synergistic integration of active and adversarial learning for effective domain alignment and noise reduction.
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。