Learning Fair Face Representation With Progressive Cross Transformer

08/11/2021
by   Yong Li, et al.
1

Face recognition (FR) has made extraordinary progress owing to the advancement of deep convolutional neural networks. However, demographic bias among different racial cohorts still challenges the practical face recognition system. The race factor has been proven to be a dilemma for fair FR (FFR) as the subject-related specific attributes induce the classification bias whilst carrying some useful cues for FR. To mitigate racial bias and meantime preserve robust FR, we abstract face identity-related representation as a signal denoising problem and propose a progressive cross transformer (PCT) method for fair face recognition. Originating from the signal decomposition theory, we attempt to decouple face representation into i) identity-related components and ii) noisy/identity-unrelated components induced by race. As an extension of signal subspace decomposition, we formulate face decoupling as a generalized functional expression model to cross-predict face identity and race information. The face expression model is further concretized by designing dual cross-transformers to distill identity-related components and suppress racial noises. In order to refine face representation, we take a progressive face decoupling way to learn identity/race-specific transformations, so that identity-unrelated components induced by race could be better disentangled. We evaluate the proposed PCT on the public fair face recognition benchmarks (BFW, RFW) and verify that PCT is capable of mitigating bias in face recognition while achieving state-of-the-art FR performance. Besides, visualization results also show that the attention maps in PCT can well reveal the race-related/biased facial regions.

READ FULL TEXT

page 1

page 3

page 11

page 13

research
11/19/2019

DebFace: De-biasing Face Recognition

We address the problem of bias in automated face recognition algorithms,...
research
05/25/2023

Human-Machine Comparison for Cross-Race Face Verification: Race Bias at the Upper Limits of Performance?

Face recognition algorithms perform more accurately than humans in some ...
research
12/16/2019

Accuracy comparison across face recognition algorithms: Where are we on measuring race bias?

Previous generations of face recognition algorithms differ in accuracy f...
research
04/19/2020

Exploring Racial Bias within Face Recognition via per-subject Adversarially-Enabled Data Augmentation

Whilst face recognition applications are becoming increasingly prevalent...
research
06/13/2020

Mitigating Face Recognition Bias via Group Adaptive Classifier

Face recognition is known to exhibit bias - subjects in certain demograp...
research
04/02/2019

Deep Learning for Face Recognition: Pride or Prejudiced?

Do very high accuracies of deep networks suggest pride of effective AI o...
research
08/14/2021

Unravelling the Effect of Image Distortions for Biased Prediction of Pre-trained Face Recognition Models

Identifying and mitigating bias in deep learning algorithms has gained s...

Please sign up or login with your details

Forgot password? Click here to reset