JMitnik/FacialDebiasing
Debiasing: Mitigating Algorithmic Facial Bias repository
This project helps researchers and practitioners in facial recognition evaluate and reduce algorithmic bias in their models. It takes facial image datasets and model configurations as input, then applies techniques to mitigate bias related to demographic factors. The output helps users understand how effectively their models have been debiased and if fairness has improved. It is ideal for data scientists, AI ethicists, or machine learning engineers working with facial analysis systems.
No commits in the last 6 months.
Use this if you are developing or deploying facial recognition technology and need to rigorously test and improve your models' fairness across different demographic groups.
Not ideal if you are looking for a pre-packaged, out-of-the-box solution for end-user facial recognition, as this tool focuses on experimental debiasing techniques.
Stars
7
Forks
6
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Oct 28, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JMitnik/FacialDebiasing"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
fairlearn/fairlearn
A Python package to assess and improve fairness of machine learning models.
Trusted-AI/AIF360
A comprehensive set of fairness metrics for datasets and machine learning models, explanations...
holistic-ai/holisticai
This is an open-source tool to assess and improve the trustworthiness of AI systems.
microsoft/responsible-ai-toolbox
Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment...
datamllab/awesome-fairness-in-ai
A curated list of awesome Fairness in AI resources