PerForm-Lab-RIT/domain-adaptation-eye-tracking

Official Implementation for the paper Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking System.

31
/ 100
Emerging

This project helps eye-tracking researchers and developers improve the accuracy of eye image segmentation models. It takes both synthetic and real-world eye image datasets and processes them to reduce the differences between simulated and actual images. The output is a more robust segmentation model that performs better on real-world eye-tracking data, benefiting those who work with eye-gaze estimation and analysis.

No commits in the last 6 months.

Use this if you are developing or evaluating eye-tracking systems and need to improve the performance of your eye image segmentation models, especially when working with a mix of synthetic and real-world eye data.

Not ideal if your primary focus is not eye-tracking or if you only work with perfectly labeled, homogeneous real-world datasets.

eye-tracking gaze-estimation computer-vision biometric-data-analysis human-computer-interaction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

17

Forks

2

Language

Python

License

Last pushed

Jun 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/PerForm-Lab-RIT/domain-adaptation-eye-tracking"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.