Analyzing Quality, Bias, and Performance in Text-to-Image Generative Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914852261330944 |
|---|---|
| author | Masrourisaadat, Nila Sedaghatkish, Nazanin Sarshartehrani, Fatemeh Fox, Edward A. |
| author_facet | Masrourisaadat, Nila Sedaghatkish, Nazanin Sarshartehrani, Fatemeh Fox, Edward A. |
| contents | Advances in generative models have led to significant interest in image synthesis, demonstrating the ability to generate high-quality images for a diverse range of text prompts. Despite this progress, most studies ignore the presence of bias. In this paper, we examine several text-to-image models not only by qualitatively assessing their performance in generating accurate images of human faces, groups, and specified numbers of objects but also by presenting a social bias analysis. As expected, models with larger capacity generate higher-quality images. However, we also document the inherent gender or social biases these models possess, offering a more complete understanding of their impact and limitations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_00138 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Analyzing Quality, Bias, and Performance in Text-to-Image Generative Models Masrourisaadat, Nila Sedaghatkish, Nazanin Sarshartehrani, Fatemeh Fox, Edward A. Artificial Intelligence Computer Vision and Pattern Recognition I.2.6; I.2.10; I.2.7; I.4.10 Advances in generative models have led to significant interest in image synthesis, demonstrating the ability to generate high-quality images for a diverse range of text prompts. Despite this progress, most studies ignore the presence of bias. In this paper, we examine several text-to-image models not only by qualitatively assessing their performance in generating accurate images of human faces, groups, and specified numbers of objects but also by presenting a social bias analysis. As expected, models with larger capacity generate higher-quality images. However, we also document the inherent gender or social biases these models possess, offering a more complete understanding of their impact and limitations. |
| title | Analyzing Quality, Bias, and Performance in Text-to-Image Generative Models |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition I.2.6; I.2.10; I.2.7; I.4.10 |
| url | https://arxiv.org/abs/2407.00138 |