OpenBias: Open-set Bias Detection in Text-to-Image Generative Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929448228487168 |
|---|---|
| author | D'Incà, Moreno Peruzzo, Elia Mancini, Massimiliano Xu, Dejia Goel, Vidit Xu, Xingqian Wang, Zhangyang Shi, Humphrey Sebe, Nicu |
| author_facet | D'Incà, Moreno Peruzzo, Elia Mancini, Massimiliano Xu, Dejia Goel, Vidit Xu, Xingqian Wang, Zhangyang Shi, Humphrey Sebe, Nicu |
| contents | Text-to-image generative models are becoming increasingly popular and accessible to the general public. As these models see large-scale deployments, it is necessary to deeply investigate their safety and fairness to not disseminate and perpetuate any kind of biases. However, existing works focus on detecting closed sets of biases defined a priori, limiting the studies to well-known concepts. In this paper, we tackle the challenge of open-set bias detection in text-to-image generative models presenting OpenBias, a new pipeline that identifies and quantifies the severity of biases agnostically, without access to any precompiled set. OpenBias has three stages. In the first phase, we leverage a Large Language Model (LLM) to propose biases given a set of captions. Secondly, the target generative model produces images using the same set of captions. Lastly, a Vision Question Answering model recognizes the presence and extent of the previously proposed biases. We study the behavior of Stable Diffusion 1.5, 2, and XL emphasizing new biases, never investigated before. Via quantitative experiments, we demonstrate that OpenBias agrees with current closed-set bias detection methods and human judgement. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_07990 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | OpenBias: Open-set Bias Detection in Text-to-Image Generative Models D'Incà, Moreno Peruzzo, Elia Mancini, Massimiliano Xu, Dejia Goel, Vidit Xu, Xingqian Wang, Zhangyang Shi, Humphrey Sebe, Nicu Computer Vision and Pattern Recognition Artificial Intelligence Text-to-image generative models are becoming increasingly popular and accessible to the general public. As these models see large-scale deployments, it is necessary to deeply investigate their safety and fairness to not disseminate and perpetuate any kind of biases. However, existing works focus on detecting closed sets of biases defined a priori, limiting the studies to well-known concepts. In this paper, we tackle the challenge of open-set bias detection in text-to-image generative models presenting OpenBias, a new pipeline that identifies and quantifies the severity of biases agnostically, without access to any precompiled set. OpenBias has three stages. In the first phase, we leverage a Large Language Model (LLM) to propose biases given a set of captions. Secondly, the target generative model produces images using the same set of captions. Lastly, a Vision Question Answering model recognizes the presence and extent of the previously proposed biases. We study the behavior of Stable Diffusion 1.5, 2, and XL emphasizing new biases, never investigated before. Via quantitative experiments, we demonstrate that OpenBias agrees with current closed-set bias detection methods and human judgement. |
| title | OpenBias: Open-set Bias Detection in Text-to-Image Generative Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2404.07990 |