Unsupervised Outlier Detection in Appearance-Based Gaze Estimation
Authors:
- 1 October 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1088-1097
Abstract
Appearance-based gaze estimation maps RGB images to estimates of gaze directions. One problem in gaze estimation is that there always exist low-quality samples (outliers) in which the eyes are barely visible. These low-quality samples are mainly caused by blinks, occlusions (e.g. by eye glasses), blur (e.g. due to motion) and failures of the eye landmark detection. Training on these outliers degrades the performance of gaze estimators, since they have no or limited information about gaze directions. It is also risky to give estimates based on these images in real-world applications, as these estimates may be unreliable. To solve this problem, we propose an algorithm that detects outliers without supervision. Based on the input images with only gaze labels, the proposed algorithm learns to predict a gaze estimates and an additional confidence score, which alleviates the impact of outliers during learning. We evaluated this algorithm on the MPIIGaze dataset and on an internal dataset. In cross-subject evaluation, our experimental results show that the proposed algorithm results in a better gaze estimator (8% improvement). The proposed algorithm is also able to reliably detect outliers during testing, with a precision of 0.71 when the recall is 0.63.Keywords
This publication has 21 references indexed in Scilit:
- GazeTheWeb2017
- Towards foveated rendering for gaze-tracked virtual realityACM Transactions on Graphics, 2016
- Eye Tracking for Everyone2016
- Learning an appearance-based gaze estimator from one million synthesised images2016
- Anticipatory robot control for efficient human-robot collaboration2016
- Appearance-based gaze estimation in the wild2015
- Pupil2014
- Learning-by-Synthesis for Appearance-Based 3D Gaze Estimation2014
- In the Eye of the Beholder: A Survey of Models for Eyes and GazeIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- General Theory of Remote Gaze Estimation Using the Pupil Center and Corneal ReflectionsIEEE Transactions on Biomedical Engineering, 2006