Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.04851 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918013093019648 |
|---|---|
| author | Vasilev, Viacheslav Arkhipkin, Vladimir Agafonova, Julia Nikulina, Tatiana Mironova, Evelina Shichanina, Alisa Gerasimenko, Nikolai Shoytov, Mikhail Dimitrov, Denis |
| author_facet | Vasilev, Viacheslav Arkhipkin, Vladimir Agafonova, Julia Nikulina, Tatiana Mironova, Evelina Shichanina, Alisa Gerasimenko, Nikolai Shoytov, Mikhail Dimitrov, Denis |
| contents | Despite the fact that popular text-to-image generation models cope well with international and general cultural queries, they have a significant knowledge gap regarding individual cultures. This is due to the content of existing large training datasets collected on the Internet, which are predominantly based on Western European or American popular culture. Meanwhile, the lack of cultural adaptation of the model can lead to incorrect results, a decrease in the generation quality, and the spread of stereotypes and offensive content. In an effort to address this issue, we examine the concept of cultural code and recognize the critical importance of its understanding by modern image generation models, an issue that has not been sufficiently addressed in the research community to date. We propose the methodology for collecting and processing the data necessary to form a dataset based on the cultural code, in particular the Russian one. We explore how the collected data affects the quality of generations in the national domain and analyze the effectiveness of our approach using the Kandinsky 3.1 text-to-image model. Human evaluation results demonstrate an increase in the level of awareness of Russian culture in the model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_04851 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CRAFT: Cultural Russian-Oriented Dataset Adaptation for Focused Text-to-Image Generation Vasilev, Viacheslav Arkhipkin, Vladimir Agafonova, Julia Nikulina, Tatiana Mironova, Evelina Shichanina, Alisa Gerasimenko, Nikolai Shoytov, Mikhail Dimitrov, Denis Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Computers and Society Machine Learning Despite the fact that popular text-to-image generation models cope well with international and general cultural queries, they have a significant knowledge gap regarding individual cultures. This is due to the content of existing large training datasets collected on the Internet, which are predominantly based on Western European or American popular culture. Meanwhile, the lack of cultural adaptation of the model can lead to incorrect results, a decrease in the generation quality, and the spread of stereotypes and offensive content. In an effort to address this issue, we examine the concept of cultural code and recognize the critical importance of its understanding by modern image generation models, an issue that has not been sufficiently addressed in the research community to date. We propose the methodology for collecting and processing the data necessary to form a dataset based on the cultural code, in particular the Russian one. We explore how the collected data affects the quality of generations in the national domain and analyze the effectiveness of our approach using the Kandinsky 3.1 text-to-image model. Human evaluation results demonstrate an increase in the level of awareness of Russian culture in the model. |
| title | CRAFT: Cultural Russian-Oriented Dataset Adaptation for Focused Text-to-Image Generation |
| topic | Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Computers and Society Machine Learning |
| url | https://arxiv.org/abs/2505.04851 |