基于概率评估与校准提升外观式视线跟踪中不确定性估计的准确性
Enhancing Accuracy of Uncertainty Estimation in Appearance-based Gaze Tracking with Probabilistic Evaluation and Calibration
把不确定性估计当作输出级条件分布匹配问题，用少量校准样本做事后校准，可直接迁移到视线跟踪、头部姿态、关键点回归等回归式视觉任务在域偏移下的置信度修正。
原文依据 we formulate uncertainty estimation as a conditional distribution problem and treat the correction process as an output-level conditional distribution matching task
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论准确的不确定性估计对于可靠的外观式视线跟踪至关重要。然而，训练与测试之间的域偏移往往导致不确定性估计不准确，这一问题在现有的不确定性感知视线跟踪模型中被忽视。为高效地克服该问题，我们将不确定性估计建模为条件分布问题，并把校正过程视为输出级的条件分布匹配任务。因此，我们引入一种数据高效的事后校准方法，使预测得到的高误差条件分布与从少量校准样本中提取的经验观测分布对齐。为更忠实地评估所得不确定性估计的准确性，我们进一步提出一种新指标——覆盖概率误差（Coverage Probability Error, CPE），用于量化预测与观测之间在分布层面的失配程度。我们在四种域偏移场景下验证了该校准流程，证明了不确定性准确性的提升及其实际收益。
英文原文摘要 1070 字符
Accurate uncertainty estimation is essential for reliable appearance-based gaze tracking. However, domain shifts between training and testing often lead to incorrect uncertainty estimates, which is a problem overlooked in existing uncertainty-aware gaze tracking models. To overcome this problem efficiently, we formulate uncertainty estimation as a conditional distribution problem and treat the correction process as an output-level conditional distribution matching task. We therefore introduce a data-efficient post-hoc calibration method to align the predicted, high-error conditional distribution with the empirically observed distribution extracted from a small set of calibration samples. To more faithfully assess the accuracy of the resulting uncertainty estimates, we further introduce a new metric, Coverage Probability Error (CPE), to quantify the distribution-level mismatch between prediction and observation. We validate the calibration procedure across four domain shift scenarios to demonstrate improved uncertainty accuracy and its practical benefits.