面向回归任务的目标无关无源域适应
Target-agnostic Source-free Domain Adaptation for Regression Tasks
- City University of Hong Kong（香港城市大学）
- The Hong Kong University of Science and Technology（香港科技大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出TASFAR，一种面向回归任务的目标无关无源域适应方法，利用预测置信度估计目标标签分布来校准源模型，在四个回归任务上平均减少22%误差，性能显著优于现有无源UDA方法。
AI中文摘要：
无监督域适应（UDA）旨在利用无标签的目标数据弥合目标域与源域之间的域差距。无源UDA去除了在目标端使用带标签源数据的要求，以保护数据隐私并节省存储。然而，现有的无源UDA工作假设已知域差距分布，因此仅限于目标感知或分类任务。为克服这一局限，我们提出TASFAR，一种面向回归任务的新型目标无关无源域适应方法。TASFAR利用预测置信度估计标签密度图作为目标标签分布，然后用其在目标域上校准源模型。我们在四个具有不同域差距的回归任务上进行了大量实验，包括不同用户的行人航位推算、不同场景下基于图像的人数统计、不同区域的房价预测以及不同出发点的出租车行程时长预测。实验表明，TASFAR显著优于最先进的无源UDA方法，在四个任务上平均减少22%的误差，并在不使用源数据的情况下达到与基于源的UDA相当的准确率。
英文摘要：
Unsupervised domain adaptation (UDA) seeks to bridge the domain gap between the target and source using unlabeled target data. Source-free UDA removes the requirement for labeled source data at the target to preserve data privacy and storage. However, work on source-free UDA assumes knowledge of domain gap distribution, and hence is limited to either target-aware or classification task. To overcome it, we propose TASFAR, a novel target-agnostic source-free domain adaptation approach for regression tasks. Using prediction confidence, TASFAR estimates a label density map as the target label distribution, which is then used to calibrate the source model on the target domain. We have conducted extensive experiments on four regression tasks with various domain gaps, namely, pedestrian dead reckoning for different users, image-based people counting in different scenes, housing-price prediction at different districts, and taxi-trip duration prediction from different departure points. TASFAR is shown to substantially outperform the state-of-the-art source-free UDA approaches by averagely reducing 22% errors for the four tasks and achieve notably comparable accuracy as source-based UDA without using source data.
