Inspecting the Geographical Representativeness of Images from Text-to-Image Models

by   Abhipsa Basu, et al.

Recent progress in generative models has resulted in models that produce both realistic as well as relevant images for most textual inputs. These models are being used to generate millions of images everyday, and hold the potential to drastically impact areas such as generative art, digital marketing and data augmentation. Given their outsized impact, it is important to ensure that the generated content reflects the artifacts and surroundings across the globe, rather than over-representing certain parts of the world. In this paper, we measure the geographical representativeness of common nouns (e.g., a house) generated through DALL.E 2 and Stable Diffusion models using a crowdsourced study comprising 540 participants across 27 countries. For deliberately underspecified inputs without country names, the generated images most reflect the surroundings of the United States followed by India, and the top generations rarely reflect surroundings from all other countries (average score less than 3 out of 5). Specifying the country names in the input increases the representativeness by 1.44 points on average for DALL.E 2 and 0.75 for Stable Diffusion, however, the overall scores for many countries still remain low, highlighting the need for future models to be more geographically inclusive. Lastly, we examine the feasibility of quantifying the geographical representativeness of generated images without conducting user studies.


page 1

page 3

page 6

page 9

page 12

page 13

page 14

page 15


Detecting Images Generated by Diffusers

This paper explores the task of detecting images generated by text-to-im...

WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models

The rapid advancement of generative models, facilitating the creation of...

Trash to Treasure: Using text-to-image models to inform the design of physical artefacts

Text-to-image generative models have recently exploded in popularity and...

Hey That's Mine Imperceptible Watermarks are Preserved in Diffusion Generated Outputs

Generative models have seen an explosion in popularity with the release ...

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models

Cutting-edge diffusion models produce images with high quality and custo...

Richer Countries and Richer Representations

We examine whether some countries are more richly represented in embeddi...

Please sign up or login with your details

Forgot password? Click here to reset