Ethically aligned Deep Learning: Unbiased Facial Aesthetic Prediction

TL;DR

This paper introduces AestheticNet, a high-performing facial attractiveness prediction model, and a novel bias-free training approach to ensure ethical and fair AI assessments of facial beauty.

Contribution

It presents a new unbiased CNN architecture for facial beauty prediction and demonstrates its effectiveness in reducing bias and improving fairness.

Findings

AestheticNet achieves a Pearson Correlation of 0.9601 in attractiveness prediction.

The proposed bias-free approach enhances fairness in facial aesthetic assessment.

The model outperforms existing competitors in accuracy and ethical considerations.

Abstract

Facial beauty prediction (FBP) aims to develop a machine that automatically makes facial attractiveness assessment. In the past those results were highly correlated with human ratings, therefore also with their bias in annotating. As artificial intelligence can have racist and discriminatory tendencies, the cause of skews in the data must be identified. Development of training data and AI algorithms that are robust against biased information is a new challenge for scientists. As aesthetic judgement usually is biased, we want to take it one step further and propose an Unbiased Convolutional Neural Network for FBP. While it is possible to create network models that can rate attractiveness of faces on a high level, from an ethical point of view, it is equally important to make sure the model is unbiased. In this work, we introduce AestheticNet, a state-of-the-art attractiveness prediction network, which significantly outperforms competitors with a Pearson Correlation of 0.9601. Additionally, we propose a new approach for generating a bias-free CNN to improve fairness in machine learning.