Header menu link for other important links
X
Unravelling the Effect of Image Distortions for Biased Prediction of Pre-trained Face Recognition Models
Puspita Majumdar, Surbhi Mittal, , Mayank Vatsa
Published in
2021
Volume: 2021-October
   
Pages: 3779 - 3788
Abstract
Identifying and mitigating bias in deep learning algorithms has gained significant popularity in the past few years due to its impact on the society. Researchers argue that models trained on balanced datasets with good representation provide equal and unbiased performance across subgroups. However, can seemingly unbiased pre-trained model become biased when input data undergoes certain distortions? For the first time, we attempt to answer this question in the context of face recognition. We provide a systematic analysis to evaluate the performance of four state-of-the-art deep face recognition models in the presence of image distortions across different gender and race subgroups. We have observed that image distortions have a relationship with the performance gap of the model across different subgroups.
About the journal
JournalProceedings of the IEEE International Conference on Computer Vision
ISSN15505499