AAAI 2024technical3 citations
FAIR-FER: A Latent Alignment Approach for Mitigating Bias in Facial Expression Recognition (Student Abstract)
Syed Sameen Ahmad Rizvi, Aryan Seth, Pratik Narang
Abstract
Facial Expression Recognition (FER) is an extensively explored research problem in the domain of computer vision and artificial intelligence. FER, a supervised learning problem, requires significant training data representative of multiple socio-cultural demographic attributes. However, most of the FER dataset consists of images annotated by humans, which propagates individual and demographic biases. This work attempts to mitigate this bias using representation learning based on latent spaces, thereby increasing a deep learning model's fairness and overall accuracy.
BibTeX
@article{Rizvi_Seth_Narang_2024, title={FAIR-FER: A Latent Alignment Approach for Mitigating Bias in Facial Expression Recognition (Student Abstract)}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/30503}, DOI={10.1609/aaai.v38i21.30503}, abstractNote={Facial Expression Recognition (FER) is an extensively explored research problem in the domain of computer vision and artificial intelligence. FER, a supervised learning problem, requires significant training data representative of multiple socio-cultural demographic attributes. However, most of the FER dataset consists of images annotated by humans, which propagates individual and demographic biases. This work attempts to mitigate this bias using representation learning based on latent spaces, thereby increasing a deep learning model’s fairness and overall accuracy.}, number={21}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Rizvi, Syed Sameen Ahmad and Seth, Aryan and Narang, Pratik}, year={2024}, month={Mar.}, pages={23633-23634} }