Volltext-Downloads (blau) und Frontdoor-Views (grau)

Ethically aligned deep learning: unbiased facial aesthetic prediction

  • 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.

Download full text files

Export metadata

Additional Services

Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Author of HS ReutlingenDanner, Michael; Weber, Thomas; Gerlach, Tobias; Rätsch, Matthias
URN:urn:nbn:de:bsz:rt2-opus4-34467
URL:https://arxiv.org/abs/2111.05149
ISSN:2331-8422
Erschienen in:arXiv
Publisher:Cornell University
Place of publication:Ithaca, New York
Document Type:Conference proceeding
Language:English
Publication year:2021
Tag:discrimination prevention; facial aesthetics; fairness in machine learning; responsible artificial intelligence; unconscious bias
Issue:Computer Vision and Pattern Recognition
Page Number:6
Article Number:2111.05149
DDC classes:004 Informatik
Open access?:Ja
Licence (German):License Logo  Creative Commons - CC BY - Namensnennung 4.0 International