The practical Domain Adaptation (DA) tasks, e.g., Partial DA (PDA), open-set DA, universal DA, and test-time adaptation, have gained increasing attention in the machine learning community. In this paper, we propose a novel approach, dubbed Adversarial Reweighting with $\alpha$-Power Maximization (ARPM), for PDA where the source domain contains private classes absent in target domain. In ARPM, we propose a novel adversarial reweighting model that adversarially learns to reweight source domain data to identify source-private class samples by assigning smaller weights to them, for mitigating potential negative transfer. Based on the adversarial reweighting, we train the transferable recognition model on the reweighted source distribution to be able to classify common class data. To reduce the prediction uncertainty of the recognition model on the target domain for PDA, we present an $\alpha$-power maximization mechanism in ARPM, which enriches the family of losses for reducing the prediction uncertainty for PDA. Extensive experimental results on five PDA benchmarks, i.e., Office-31, Office-Home, VisDA-2017, ImageNet-Caltech, and DomainNet, show that our method is superior to recent PDA methods. Ablation studies also confirm the effectiveness of components in our approach. To theoretically analyze our method, we deduce an upper bound of target domain expected error for PDA, which is approximately minimized in our approach. We further extend ARPM to open-set DA, universal DA, and test time adaptation, and verify the usefulness through experiments.

翻译：实际域适应任务，如部分域适应、开放集域适应、通用域适应以及测试时适应，正日益受到机器学习领域的关注。本文针对源域包含目标域不存在私有类别的部分域适应问题，提出一种称为基于$\alpha$-幂最大化的对抗性重加权方法。在该方法中，我们构建了一种新颖的对抗性重加权模型，通过对抗性学习对源域数据赋予不同权重，对源域私有类样本分配较小权重，从而有效缓解潜在的负迁移。基于该对抗性重加权机制，我们在重加权后的源域分布上训练可迁移识别模型，使其能够正确分类公共类数据。为降低部分域适应中识别模型在目标域上的预测不确定性，我们提出$\alpha$-幂最大化机制，该机制丰富了减少预测不确定性的损失函数族。在Office-31、Office-Home、VisDA-2017、ImageNet-Caltech和DomainNet五个部分域适应基准上的大量实验结果表明，本方法优于现有部分域适应方法。消融研究进一步验证了方法各组件的有效性。为进行理论分析，我们推导了部分域适应中目标域期望误差的上界，该上界在本方法中近似最小化。我们将该方法进一步扩展至开放集域适应、通用域适应和测试时适应场景，并通过实验验证其有效性。