Enhancing accuracy of uncertainty estimation in appearance-based gaze tracking with probabilistic evaluation and calibration

TL;DR

This paper improves the reliability of appearance-based gaze tracking by introducing a probabilistic evaluation metric and a calibration method to reduce bias in uncertainty estimates, validated on two datasets.

Contribution

It proposes a new evaluation metric for uncertainty assessment and a calibration strategy to enhance uncertainty estimation accuracy in gaze tracking models.

Findings

The evaluation metric effectively measures uncertainty quality.

Calibration reduces bias in uncertainty estimates.

Improved uncertainty estimation leads to more reliable gaze tracking.

Abstract

Accurately knowing uncertainties in appearance-based gaze tracking is critical for ensuring reliable downstream applications. Due to the lack of individual uncertainty labels, current uncertainty-aware approaches adopt probabilistic models to acquire uncertainties by following distributions in the training dataset. Without regulations, this approach lets the uncertainty model build biases and overfits the training data, leading to poor performance when deployed. We first presented a strict proper evaluation metric from the probabilistic perspective based on comparing the coverage probability between prediction and observation to provide quantitative evaluation for better assessment on the inferred uncertainties. We then proposed a correction strategy based on probability calibration to mitigate biases in the estimated uncertainties of the trained models. Finally, we demonstrated the effectiveness of the correction strategy with experiments performed on two popular gaze estimation datasets with distinctive image characteristics caused by data collection settings.