We present a framework that uses GAN-augmented images to complement certain specific attributes, usually underrepresented, for machine learning model training. This allows us to improve inference quality over those attributes for the facial recognition tasks.
@article{arxiv.2205.06873,
title = {Using Augmented Face Images to Improve Facial Recognition Tasks},
author = {Shuo Cheng and Guoxian Song and Wan-Chun Ma and Chao Wang and Linjie Luo},
journal= {arXiv preprint arXiv:2205.06873},
year = {2022}
}
Comments
CHI 2022 Workshop: AI-Generated Characters: Putting Deepfakes to Good Use