Analysis of Bias in Deep Learning Facial Beauty Regressors
Not on the map. Why?
Abstract (arXiv)
Bias can be introduced to AI systems even from seemingly balanced sources, and AI facial beauty prediction is subject to ethnicity-based bias. This work sounds warnings about AI's role in shaping aesthetic norms while providing potential pathways toward equitable beauty technologies through comparative analysis of models trained on SCUT-FBP5500 and MEBeauty datasets. Employing rigorous statistical validation (Kruskal-Wallis H-tests, post hoc Dunn analyses). It is demonstrated that both models exhibit significant prediction disparities across ethnic groups (p < 0.001), even when evaluated on the balanced FairFace dataset. Cross-dataset validation shows algorithmic amplification of societal beauty biases rather than mitigation based on prediction and error parity. The findings underscore the inadequacy of current AI beauty prediction approaches, with only 4.8-9.5% of inter-group comparisons satisfying distributional parity criteria. Mitigation strategies are proposed and discussed in detail.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 7 of its 19 references that are in the map. First posted on arXiv 29 Sep 2025.
Builds on
7 of 19 references.
References · 7
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
- 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 903
- 2018SCUT-FBP5500: A Diverse Benchmark Dataset for Multi-Paradigm Facial Beauty Predictioncited by 33
- 2024Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibriumcited by 9
- 2021End-To-End Bias Mitigation: Removing Gender Bias in Deep Learningcited by 6
- 2024Enforcing Equity in Neural Climate Emulatorscited by 1
Built on by
Not cited yet.