Overcome ethnic discrimination with unbiased machine learning for facial data sets
- AI-based prediction and recommender systems are widely used in various industry sectors. However, general acceptance of AI-enabled systems is still widely uninvestigated. Therefore, firstly we conducted a survey with 559 respondents. Findings suggested that AI-enabled systems should be fair, transparent, consider personality traits and perform tasks efficiently. Secondly, we developed a system for the Facial Beauty Prediction (FBP) benchmark that automatically evaluates facial attractiveness. As our previous experiments have proven, these results are usually highly correlated with human ratings. Consequently they also reflect human bias in annotations. An upcoming challenge for scientists is to provide training data and AI algorithms that can withstand distorted information. In this work, we introduce AntiDiscriminationNet (ADN), a superior attractiveness prediction network. We propose a new method to generate an unbiased convolutional neural network (CNN) to improve the fairn ess of machine learning in facial dataset. To train unbiased networks we generate synthetic images and weight training data for anti-discrimination assessments towards different ethnicities. Additionally, we introduce an approach with entropy penalty terms to reduce the bias of our CNN. Our research provides insights in how to train and build fair machine learning models for facial image analysis by minimising implicit biases. Our AntiDiscriminationNet finally outperforms all competitors in the FBP benchmark by achieving a Pearson correlation coefficient of PCC = 0.9601.
Author of HS Reutlingen | Danner, Michael; Hadžić, Bakir; Weber, Thomas; Rätsch, Matthias |
---|---|
URN: | urn:nbn:de:bsz:rt2-opus4-41782 |
DOI: | https://doi.org/10.5220/0011624900003417 |
ISBN: | 978-989-758-634-7 |
ISSN: | 2184-4321 |
Erschienen in: | Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5 VISAPP: VISAPP, 464-471, 2023 , Lisbon, Portugal |
Publisher: | SciTePress |
Place of publication: | Setúbal, Portugal |
Document Type: | Conference proceeding |
Language: | English |
Publication year: | 2023 |
Tag: | AI-acceptance analysis; acceptance research; debiasing training data; facial data sets; fairness; trustworthy AI; unbiased machine learning |
Volume: | 5 |
Page Number: | 8 |
First Page: | 464 |
Last Page: | 471 |
DDC classes: | 004 Informatik |
Open access?: | Ja |
Licence (German): | Creative Commons - CC BY-NC-ND - Namensnennung - Nicht kommerziell - Keine Bearbeitungen 4.0 International |