Abstract
Deep learning appearance-based 3D gaze estimation is gaining popularity due to its minimal hardware requirements and being free of constraint. Unreliable and overconfident inferences, however, still limit the adoption of this gaze estimation method. To address the unreliable and overconfident issues, we introduce a confidence-aware model that predicts uncertainties together with gaze angle estimations. We also introduce a novel effectiveness evaluation method based on the causality between eye feature degradation and the rise in inference uncertainty to assess the uncertainty estimation. Our confidence-aware model demonstrates reliable uncertainty estimations while providing angular estimation accuracies on par with the state-of-the-art. Compared with the existing statistical uncertainty-angular-error evaluation metric, the proposed effectiveness evaluation approach can more effectively judge inferred uncertainties' performance at each prediction.
Abstract (translated)
Deep learning 基于外观的三维目光估计因其硬件要求最小且不受限制而越来越受欢迎。然而,不可靠的和过于自信的决策仍然限制着这种方法的采用。为了解决这些不可靠和过于自信的问题,我们引入了一种具有自我意识的模型,它可以同时预测不确定性和目光角度估计。我们还介绍了一种基于 eye feature 退化和推断不确定性的上升的因果关系的新有效性评估方法,以评估不确定性估计。我们的具有自我意识的模型表现出可靠的不确定性估计,同时提供与当前最先进的准确性相当的角估计精度。与现有的统计不确定性-角误差评估度量相比,我们提出的有效性评估方法可以更有效地评估推断不确定性在每个预测中的性能。
URL
https://arxiv.org/abs/2303.10062