Examining Pathological Bias in a Generative Adversarial Network Discriminator: A Case Study on a StyleGAN3 Model

• URL: http://arxiv.org/abs/2402.09786v3
• Date: Tue, 12 Mar 2024 13:36:23 GMT
• Title: Examining Pathological Bias in a Generative Adversarial Network Discriminator: A Case Study on a StyleGAN3 Model
• Authors: Alvin Grissom II, Ryan F. Lei, Matt Gusdorff, Jeova Farias Sales Rocha Neto, Bailey Lin, Ryan Trotter
• Abstract summary: Generative adversarial networks (GANs) generate photorealistic faces that are often indistinguishable by humans from real faces. We find pathological internal color and luminance biases in the discriminator of a pre-trained StyleGAN3-r model. We also find that the discriminator systematically stratifies scores by both image- and face-level qualities and that this disproportionately affects images across gender, race, and other categories.
• Score: 0.3345450283591703
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative adversarial networks (GANs) generate photorealistic faces that are often indistinguishable by humans from real faces. While biases in machine learning models are often assumed to be due to biases in training data, we find pathological internal color and luminance biases in the discriminator of a pre-trained StyleGAN3-r model that are not explicable by the training data. We also find that the discriminator systematically stratifies scores by both image- and face-level qualities and that this disproportionately affects images across gender, race, and other categories. We examine axes common in research on stereotyping in social psychology.

Related papers

• Less can be more: representational vs. stereotypical gender bias in facial expression recognition [3.9698529891342207]
  Machine learning models can inherit biases from their training data, leading to discriminatory or inaccurate predictions. This paper investigates the propagation of demographic biases from datasets into machine learning models. We focus on the gender demographic component, analyzing two types of bias: representational and stereotypical.
  arXiv  Detail & Related papers  (2024-06-25T09:26:49Z)
• Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition [107.58227666024791]
  Face recognition systems are widely deployed in safety-critical applications, including law enforcement. They exhibit bias across a range of socio-demographic dimensions, such as gender and race. Previous works on bias mitigation largely focused on pre-processing the training data.
  arXiv  Detail & Related papers  (2022-10-18T15:46:05Z)
• Gender Stereotyping Impact in Facial Expression Recognition [1.5340540198612824]
  In recent years, machine learning-based models have become the most popular approach to Facial Expression Recognition (FER) In publicly available FER datasets, apparent gender representation is usually mostly balanced, but their representation in the individual label is not. We generate derivative datasets with different amounts of stereotypical bias by altering the gender proportions of certain labels. We observe a discrepancy in the recognition of certain emotions between genders of up to $29 %$ under the worst bias conditions.
  arXiv  Detail & Related papers  (2022-10-11T10:52:23Z)
• Studying Bias in GANs through the Lens of Race [91.95264864405493]
  We study how the performance and evaluation of generative image models are impacted by the racial composition of their training datasets. Our results show that the racial compositions of generated images successfully preserve that of the training data. However, we observe that truncation, a technique used to generate higher quality images during inference, exacerbates racial imbalances in the data.
  arXiv  Detail & Related papers  (2022-09-06T22:25:56Z)
• Are Commercial Face Detection Models as Biased as Academic Models? [64.71318433419636]
  We compare academic and commercial face detection systems, specifically examining robustness to noise. We find that state-of-the-art academic face detection models exhibit demographic disparities in their noise robustness. We conclude that commercial models are always as biased or more biased than an academic model.
  arXiv  Detail & Related papers  (2022-01-25T02:21:42Z)
• Unravelling the Effect of Image Distortions for Biased Prediction of Pre-trained Face Recognition Models [86.79402670904338]
  We evaluate the performance of four state-of-the-art deep face recognition models in the presence of image distortions. We have observed that image distortions have a relationship with the performance gap of the model across different subgroups.
  arXiv  Detail & Related papers  (2021-08-14T16:49:05Z)
• Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases [3.0349733976070015]
  We develop a novel method for quantifying biased associations between representations of social concepts and attributes in images. We find that state-of-the-art unsupervised models trained on ImageNet, a popular benchmark image dataset, automatically learn racial, gender, and intersectional biases.
  arXiv  Detail & Related papers  (2020-10-28T15:55:49Z)
• Learning from Failure: Training Debiased Classifier from Biased Classifier [76.52804102765931]
  We show that neural networks learn to rely on spurious correlation only when it is "easier" to learn than the desired knowledge. We propose a failure-based debiasing scheme by training a pair of neural networks simultaneously. Our method significantly improves the training of the network against various types of biases in both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2020-07-06T07:20:29Z)
• InsideBias: Measuring Bias in Deep Networks and Application to Face Gender Biometrics [73.85525896663371]
  This work explores the biases in learning processes based on deep neural network architectures. We employ two gender detection models based on popular deep neural networks. We propose InsideBias, a novel method to detect biased models.
  arXiv  Detail & Related papers  (2020-04-14T15:20:50Z)
• Imperfect ImaGANation: Implications of GANs Exacerbating Biases on Facial Data Augmentation and Snapchat Selfie Lenses [20.36399588424965]
  We show that popular Generative Adversarial Networks (GANs) exacerbate biases along the axes of gender and skin tone when given a skewed distribution of face-shots. GANs also exacerbate biases by lightening skin color of non-white faces and transforming female facial features to be masculine when generating faces of engineering professors.
  arXiv  Detail & Related papers  (2020-01-26T21:57:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.