Mitigating stereotypical biases in text to image generative systems

• URL: http://arxiv.org/abs/2310.06904v1
• Date: Tue, 10 Oct 2023 18:01:52 GMT
• Title: Mitigating stereotypical biases in text to image generative systems
• Authors: Piero Esposito, Parmida Atighehchian, Anastasis Germanidis and Deepti Ghadiyaram
• Abstract summary: We do this by finetuning text-to-image models on synthetic data that varies in perceived skin tones and genders constructed from diverse text prompts. Our diversity finetuned (DFT) model improves the group fairness metric by 150% for perceived skin tone and 97.7% for perceived gender.
• Score: 10.068823600548157
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: State-of-the-art generative text-to-image models are known to exhibit social biases and over-represent certain groups like people of perceived lighter skin tones and men in their outcomes. In this work, we propose a method to mitigate such biases and ensure that the outcomes are fair across different groups of people. We do this by finetuning text-to-image models on synthetic data that varies in perceived skin tones and genders constructed from diverse text prompts. These text prompts are constructed from multiplicative combinations of ethnicities, genders, professions, age groups, and so on, resulting in diverse synthetic data. Our diversity finetuned (DFT) model improves the group fairness metric by 150% for perceived skin tone and 97.7% for perceived gender. Compared to baselines, DFT models generate more people with perceived darker skin tone and more women. To foster open research, we will release all text prompts and code to generate training images.

Related papers

• GRADE: Quantifying Sample Diversity in Text-to-Image Models [66.12068246962762]
  We propose GRADE: Granular Attribute Diversity Evaluation, an automatic method for quantifying sample diversity. We measure the overall diversity of 12 T2I models using 400 concept-attribute pairs, revealing that all models display limited variation. Our work proposes a modern, semantically-driven approach to measure sample diversity and highlights the stunning homogeneity in outputs by T2I models.
  arXiv  Detail & Related papers  (2024-10-29T23:10:28Z)
• The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Intervention [61.80236015147771]
  We quantify the trade-off between using diversity interventions and preserving demographic factuality in T2I models. Experiments on DoFaiR reveal that diversity-oriented instructions increase the number of different gender and racial groups. We propose Fact-Augmented Intervention (FAI) to reflect on verbalized or retrieved factual information about gender and racial compositions of generation subjects in history.
  arXiv  Detail & Related papers  (2024-06-29T09:09:42Z)
• Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Images [10.385717398477414]
  We present a new dataset PAIRS (PArallel Images for eveRyday Scenarios) The PAIRS dataset contains sets of AI-generated images of people, such that the images are highly similar in terms of background and visual content, but differ along the dimensions of gender and race. By querying the LVLMs with such images, we observe significant differences in the responses according to the perceived gender or race of the person depicted.
  arXiv  Detail & Related papers  (2024-02-08T16:11:23Z)
• AI-generated faces influence gender stereotypes and racial homogenization [1.6647208383676708]
  We document significant biases in Stable Diffusion across six races, two genders, 32 professions, and eight attributes. This analysis reveals significant racial homogenization depicting nearly all Middle Eastern men as bearded, brown-skinned, and wearing traditional attire. We propose debiasing solutions that allow users to specify the desired distributions of race and gender when generating images.
  arXiv  Detail & Related papers  (2024-02-01T20:32:14Z)
• Exposing Bias in Online Communities through Large-Scale Language Models [3.04585143845864]
  This work uses the flaw of bias in language models to explore the biases of six different online communities. The bias of the resulting models is evaluated by prompting the models with different demographics and comparing the sentiment and toxicity values of these generations. This work not only affirms how easily bias is absorbed from training data but also presents a scalable method to identify and compare the bias of different datasets or communities.
  arXiv  Detail & Related papers  (2023-06-04T08:09:26Z)
• Auditing Gender Presentation Differences in Text-to-Image Models [54.16959473093973]
  We study how gender is presented differently in text-to-image models. By probing gender indicators in the input text, we quantify the frequency differences of presentation-centric attributes. We propose an automatic method to estimate such differences.
  arXiv  Detail & Related papers  (2023-02-07T18:52:22Z)
• How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions? [67.97752431429865]
  We study the effect on the diversity of the generated images when adding ethical intervention. Preliminary studies indicate that a large change in the model predictions is triggered by certain phrases such as 'irrespective of gender'
  arXiv  Detail & Related papers  (2022-10-27T07:32:39Z)
• DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models [73.12069620086311]
  We investigate the visual reasoning capabilities and social biases of text-to-image models. First, we measure three visual reasoning skills: object recognition, object counting, and spatial relation understanding. Second, we assess the gender and skin tone biases by measuring the gender/skin tone distribution of generated images.
  arXiv  Detail & Related papers  (2022-02-08T18:36:52Z)
• Multi-Dimensional Gender Bias Classification [67.65551687580552]
  Machine learning models can inadvertently learn socially undesirable patterns when training on gender biased text. We propose a general framework that decomposes gender bias in text along several pragmatic and semantic dimensions. Using this fine-grained framework, we automatically annotate eight large scale datasets with gender information.
  arXiv  Detail & Related papers  (2020-05-01T21:23:20Z)

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.