# Stereotype-Free Classification of Fictitious Faces

arXiv: https://arxiv.org/abs/2005.02157 · HTML: https://mlsanity.com/paper/2005.02157/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Apr 2020.

## Built on by (most cited first, 4 of 4)

- [Improving Neural Networks for Time Series Forecasting using Data Augmentation and AutoML](https://mlsanity.com/paper/2103.01992/) (2021)
- [Occupancy Detection in Room Using Sensor Data](https://mlsanity.com/paper/2101.03616/) (2021)
- [Generative Adversarial Network Applications in Creating a Meta-Universe](https://mlsanity.com/paper/2201.09152/) (2022)
- [Learning Unbiased Image Segmentation: A Case Study with Plain Knee Radiographs](https://mlsanity.com/paper/2308.04356/) (2023)

## Abstract (arXiv)

Equal Opportunity and Fairness are receiving increasing attention in artificial intelligence. Stereotyping is another source of discrimination, which yet has been unstudied in literature. GAN-made faces would be exposed to such discrimination, if they are classified by human perception. It is possible to eliminate the human impact on fictitious faces classification task by the use of statistical approaches. We present a novel approach through penalized regression to label stereotype-free GAN-generated synthetic unlabeled images. The proposed approach aids labeling new data (fictitious output images) by minimizing a penalized version of the least squares cost function between realistic pictures and target pictures.