Few-shot Adaptive Gaze Estimation

05/06/2019
by   Seonwook Park, et al.
6

Inter-personal anatomical differences limit the accuracy of person-independent gaze estimation networks. Yet there is a need to lower gaze errors further to enable applications requiring higher quality. Further gains can be achieved by personalizing gaze networks, ideally with few calibration samples. However, over-parameterized neural networks are not amenable to learning from few examples as they can quickly over-fit. We embrace these challenges and propose a novel framework for Few-shot Adaptive GaZE Estimation (FAZE) for learning person-specific gaze networks with very few (less than 9) calibration samples. FAZE learns a rotation-aware latent representation of gaze via a disentangling encoder-decoder architecture along with a highly adaptable gaze estimator trained using meta-learning. It is capable of adapting to any new person to yield significant performance gains with as few as 3 samples, yielding state-of-the-art performance of 3.18-deg on GazeCapture, a 19 improvement over prior art.

READ FULL TEXT

page 4

page 5

research
07/02/2018

Appearance-Based 3D Gaze Estimation with Personal Calibration

We propose a way to incorporate personal calibration into a deep learnin...
research
10/10/2021

FLAME: Facial Landmark Heatmap Activated Multimodal Gaze Estimation

3D gaze estimation is about predicting the line of sight of a person in ...
research
09/27/2021

Effect Of Personalized Calibration On Gaze Estimation Using Deep-Learning

With the increase in computation power and the development of new state-...
research
01/09/2022

Resolving Camera Position for a Practical Application of Gaze Estimation on Edge Devices

Most Gaze estimation research only works on a setup condition that a cam...
research
04/24/2019

Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesis

As an indicator of human attention gaze is a subtle behavioral cue which...
research
06/27/2021

The Story in Your Eyes: An Individual-difference-aware Model for Cross-person Gaze Estimation

We propose a novel method on refining cross-person gaze prediction task ...

Please sign up or login with your details

Forgot password? Click here to reset