Gaze Estimation with an Ensemble of Four Architectures



This paper presents a method for gaze estimation according to face images.We train several gaze estimators adopting four different network architectures, including an architecture designed for gaze estimation (i.e.,iTracker-MHSA) and three originally designed for general computer vision tasks(i.e., BoTNet, HRNet, ResNeSt). Then, we select the best six estimators and ensemble their predictions through a linear combination.The method ranks the first on the leader-board of ETH-XGaze Competition, achieving an average angular error of $3.11^{\circ}$ on the ETH-XGaze test set.

Report for Winner in ETH-XGaze Challenge CVPR 2021 Gaze WorkShop