Skip to content

matisandacz/Debiasing-Facial-Detection-Systems

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 

Repository files navigation

Debiasing-Facial-Detection-Systems

In this lab, we'll investigate one recently published approach to addressing algorithmic bias. We'll build a facial detection model that learns the latent variables underlying face image datasets and uses this to adaptively re-sample the training data, thus mitigating any biases that may be present in order to train a debiased model.

The following picture compares the accuracy on each of "Dark Male", "Dark Female", "Light Male", and "Light Female" demographics being classified as a face using a standard CNN classifier and using our debiased model.

bias

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published