Fair Multi-Exit Framework for Facial Attribute Classification

01/08/2023
by   Ching-Hao Chiu, et al.
0

Fairness has become increasingly pivotal in facial recognition. Without bias mitigation, deploying unfair AI would harm the interest of the underprivileged population. In this paper, we observe that though the higher accuracy that features from the deeper layer of a neural networks generally offer, fairness conditions deteriorate as we extract features from deeper layers. This phenomenon motivates us to extend the concept of multi-exit framework. Unlike existing works mainly focusing on accuracy, our multi-exit framework is fairness-oriented, where the internal classifiers are trained to be more accurate and fairer. During inference, any instance with high confidence from an internal classifier is allowed to exit early. Moreover, our framework can be applied to most existing fairness-aware frameworks. Experiment results show that the proposed framework can largely improve the fairness condition over the state-of-the-art in CelebA and UTK Face datasets.

READ FULL TEXT

page 3

page 6

research
06/26/2023

Toward Fairness Through Fair Multi-Exit Framework for Dermatological Disease Diagnosis

Fairness has become increasingly pivotal in medical image recognition. H...
research
02/12/2021

Technical Challenges for Training Fair Neural Networks

As machine learning algorithms have been widely deployed across applicat...
research
07/20/2020

Investigating Bias and Fairness in Facial Expression Recognition

Recognition of expressions of emotions and affect from facial images is ...
research
09/14/2022

CAT: Controllable Attribute Translation for Fair Facial Attribute Classification

As the social impact of visual recognition has been under scrutiny, seve...
research
07/07/2022

Enhancing Fairness of Visual Attribute Predictors

The performance of deep neural networks for image recognition tasks such...
research
12/22/2020

Unbiased Subdata Selection for Fair Classification: A Unified Framework and Scalable Algorithms

As an important problem in modern data analytics, classification has wit...
research
05/27/2022

Prototype Based Classification from Hierarchy to Fairness

Artificial neural nets can represent and classify many types of data but...

Please sign up or login with your details

Forgot password? Click here to reset