Multi-Group Proportional Representation for Text-to-Image Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908384795557888 |
|---|---|
| author | Jung, Sangwon Oesterling, Alex Verdun, Claudio Mayrink Vithana, Sajani Moon, Taesup Calmon, Flavio P. |
| author_facet | Jung, Sangwon Oesterling, Alex Verdun, Claudio Mayrink Vithana, Sajani Moon, Taesup Calmon, Flavio P. |
| contents | Text-to-image (T2I) generative models can create vivid, realistic images from textual descriptions. As these models proliferate, they expose new concerns about their ability to represent diverse demographic groups, propagate stereotypes, and efface minority populations. Despite growing attention to the "safe" and "responsible" design of artificial intelligence (AI), there is no established methodology to systematically measure and control representational harms in image generation. This paper introduces a novel framework to measure the representation of intersectional groups in images generated by T2I models by applying the Multi-Group Proportional Representation (MPR) metric. MPR evaluates the worst-case deviation of representation statistics across given population groups in images produced by a generative model, allowing for flexible and context-specific measurements based on user requirements. We also develop an algorithm to optimize T2I models for this metric. Through experiments, we demonstrate that MPR can effectively measure representation statistics across multiple intersectional groups and, when used as a training objective, can guide models toward a more balanced generation across demographic groups while maintaining generation quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_24023 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Group Proportional Representation for Text-to-Image Models Jung, Sangwon Oesterling, Alex Verdun, Claudio Mayrink Vithana, Sajani Moon, Taesup Calmon, Flavio P. Computer Vision and Pattern Recognition Artificial Intelligence Text-to-image (T2I) generative models can create vivid, realistic images from textual descriptions. As these models proliferate, they expose new concerns about their ability to represent diverse demographic groups, propagate stereotypes, and efface minority populations. Despite growing attention to the "safe" and "responsible" design of artificial intelligence (AI), there is no established methodology to systematically measure and control representational harms in image generation. This paper introduces a novel framework to measure the representation of intersectional groups in images generated by T2I models by applying the Multi-Group Proportional Representation (MPR) metric. MPR evaluates the worst-case deviation of representation statistics across given population groups in images produced by a generative model, allowing for flexible and context-specific measurements based on user requirements. We also develop an algorithm to optimize T2I models for this metric. Through experiments, we demonstrate that MPR can effectively measure representation statistics across multiple intersectional groups and, when used as a training objective, can guide models toward a more balanced generation across demographic groups while maintaining generation quality. |
| title | Multi-Group Proportional Representation for Text-to-Image Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2505.24023 |