Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking Systems
This work addresses the domain adaptation challenge in eye-tracking systems, which is incremental as it builds on existing methods for improving segmentation with synthetic data.
The paper tackles the problem of eye image segmentation for eye tracking by addressing the generalization gap between synthetic and real-world data, achieving robust performance improvements through dataset pruning based on distribution overlap.
Eye image segmentation is a critical step in eye tracking that has great influence over the final gaze estimate. Segmentation models trained using supervised machine learning can excel at this task, their effectiveness is determined by the degree of overlap between the narrow distributions of image properties defined by the target dataset and highly specific training datasets, of which there are few. Attempts to broaden the distribution of existing eye image datasets through the inclusion of synthetic eye images have found that a model trained on synthetic images will often fail to generalize back to real-world eye images. In remedy, we use dimensionality-reduction techniques to measure the overlap between the target eye images and synthetic training data, and to prune the training dataset in a manner that maximizes distribution overlap. We demonstrate that our methods result in robust, improved performance when tackling the discrepancy between simulation and real-world data samples.