COSI 159 Assignment 4
In this section, I used DeepFace to predict the age of individuals in the Fairface dataset and measured the accuracy of the predictions. Additionally, I analyzed the potential bias of the DeepFace model with respect to gender and race.
Run the deepface to predict the age
Perform the evaluation and compute the accuracy
Perform the evaluation for each subgroups (Race & Gender), and compute the accuracy and standard deviation
[1]K. Ucla, J. Jungseock, and Ucla, “FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age for Bias Measurement and Mitigation.” Available: https://openaccess.thecvf.com/content/WACV2021/papers/Karkkainen_FairFace_Face_Attribute_Dataset_for_Balanced_Race_Gender_and_Age_WACV_2021_paper.pdf
[2]S. I. Serengil and A. Ozpinar, “LightFace: A Hybrid Deep Face Recognition Framework,” IEEE Xplore, Oct. 01, 2020. https://ieeexplore.ieee.org/document/9259802