回归任务中无监督域自适应的不确定性引导对齐
Uncertainty-Guided Alignment for Unsupervised Domain Adaptation in Regression
- EPFL（洛桑联邦理工学院）
- Intelligent Maintenance and Operations Systems（智能维护与运营系统（机构））
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出不确定性引导对齐（UGA），将证据深度学习预测的不确定性融入特征对齐过程，以解决回归任务无监督域自适应中传统特征对齐失效和特征坍缩问题，并在多个基准上取得优于现有方法的性能。
AI中文摘要：
回归任务的无监督域自适应（UDAR）旨在将模型从有标签的源域适配到无标签的目标域，以完成回归任务。传统的特征对齐方法在分类任务中取得了成功，但由于回归特征具有相关性，这些方法在回归任务中往往效果不佳。为应对这一挑战，我们提出了不确定性引导对齐（UGA），这是一种将预测不确定性融入特征对齐过程的新方法。UGA采用证据深度学习来同时预测目标值及其相关的不确定性。这些不确定性信息引导对齐过程，并在嵌入空间内融合信息，从而有效缓解分布外场景中的特征坍缩等问题。我们在两个计算机视觉基准以及一个跨不同制造商和工作温度的电池荷电状态预测的真实世界任务上对UGA进行了评估。在52个迁移任务中，UGA平均性能优于现有的最先进方法。我们的方法不仅提升了适配性能，还提供了校准良好的不确定性估计。
英文摘要：
Unsupervised Domain Adaptation for Regression (UDAR) aims to adapt models from a labeled source domain to an unlabeled target domain for regression tasks. Traditional feature alignment methods, successful in classification, often prove ineffective for regression due to the correlated nature of regression features. To address this challenge, we propose Uncertainty-Guided Alignment (UGA), a novel method that integrates predictive uncertainty into the feature alignment process. UGA employs Evidential Deep Learning to predict both target values and their associated uncertainties. This uncertainty information guides the alignment process and fuses information within the embedding space, effectively mitigating issues such as feature collapse in out-of-distribution scenarios. We evaluate UGA on two computer vision benchmarks and a real-world battery state-of-charge prediction across different manufacturers and operating temperatures. Across 52 transfer tasks, UGA on average outperforms existing state-of-the-art methods. Our approach not only improves adaptation performance but also provides well-calibrated uncertainty estimates.
