Search Results for author:
Found 4 papers, 0 papers with code
A Self-Supervised Learning Pipeline for Demographically Fair Facial Attribute Classification
The proposed bias mitigation techniques are mostly based on supervised learning, which requires a large amount of labeled training data for generalizability and scalability.
Deep Generative Views to Mitigate Gender Classification Bias Across Gender-Race Groups
Published studies have suggested the bias of automated face-based gender classification algorithms across gender-race groups.
Ranked #1 on
Fairness
on MORPH
(using extra training data)
Harnessing Unlabeled Data to Improve Generalization of Biometric Gender and Age Classifiers
However, these deep learning models need large amount of labeled data for model training and optimum parameter estimation.
An Experimental Evaluation on Deepfake Detection using Deep Face Recognition
Experimental investigations on challenging Celeb-DF and FaceForensics++ deepfake datasets suggest the efficacy of deep face recognition in identifying deepfakes over two-class CNNs and the ocular modality.
