AI's Blind Spots: Geographic Knowledge and Diversity Deficit in Generated Urban Scenario
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908414888640512 |
|---|---|
| author | Beneduce, Ciro Luca, Massimiliano Lepri, Bruno |
| author_facet | Beneduce, Ciro Luca, Massimiliano Lepri, Bruno |
| contents | Image generation models are revolutionizing many domains, and urban analysis and design is no exception. While such models are widely adopted, there is a limited literature exploring their geographic knowledge, along with the biases they embed. In this work, we generated 150 synthetic images for each state in the USA and related capitals using FLUX 1 and Stable Diffusion 3.5, two state-of-the-art models for image generation. We embed each image using DINO-v2 ViT-S/14 and the Fréchet Inception Distances to measure the similarity between the generated images. We found that while these models have implicitly learned aspects of USA geography, if we prompt the models to generate an image for "United States" instead of specific cities or states, the models exhibit a strong representative bias toward metropolis-like areas, excluding rural states and smaller cities. {\color{black} In addition, we found that models systematically exhibit some entity-disambiguation issues with European-sounding names like Frankfort or Devon. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_16898 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AI's Blind Spots: Geographic Knowledge and Diversity Deficit in Generated Urban Scenario Beneduce, Ciro Luca, Massimiliano Lepri, Bruno Artificial Intelligence Computer Vision and Pattern Recognition Computers and Society Image generation models are revolutionizing many domains, and urban analysis and design is no exception. While such models are widely adopted, there is a limited literature exploring their geographic knowledge, along with the biases they embed. In this work, we generated 150 synthetic images for each state in the USA and related capitals using FLUX 1 and Stable Diffusion 3.5, two state-of-the-art models for image generation. We embed each image using DINO-v2 ViT-S/14 and the Fréchet Inception Distances to measure the similarity between the generated images. We found that while these models have implicitly learned aspects of USA geography, if we prompt the models to generate an image for "United States" instead of specific cities or states, the models exhibit a strong representative bias toward metropolis-like areas, excluding rural states and smaller cities. {\color{black} In addition, we found that models systematically exhibit some entity-disambiguation issues with European-sounding names like Frankfort or Devon. |
| title | AI's Blind Spots: Geographic Knowledge and Diversity Deficit in Generated Urban Scenario |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition Computers and Society |
| url | https://arxiv.org/abs/2506.16898 |