How Culturally Aware are Vision-Language Models?
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915143869267968 |
|---|---|
| author | Burda-Lassen, Olena Chadha, Aman Goswami, Shashank Jain, Vinija |
| author_facet | Burda-Lassen, Olena Chadha, Aman Goswami, Shashank Jain, Vinija |
| contents | An image is often considered worth a thousand words, and certain images can tell rich and insightful stories. Can these stories be told via image captioning? Images from folklore genres, such as mythology, folk dance, cultural signs, and symbols, are vital to every culture. Our research compares the performance of four popular vision-language models (GPT-4V, Gemini Pro Vision, LLaVA, and OpenFlamingo) in identifying culturally specific information in such images and creating accurate and culturally sensitive image captions. We also propose a new evaluation metric, the Cultural Awareness Score (CAS), which measures the degree of cultural awareness in image captions. We provide a dataset MOSAIC-1.5k labeled with ground truth for images containing cultural background and context and a labeled dataset with assigned Cultural Awareness Scores that can be used with unseen data. Creating culturally appropriate image captions is valuable for scientific research and can be beneficial for many practical applications. We envision our work will promote a deeper integration of cultural sensitivity in AI applications worldwide. By making the dataset and Cultural Awareness Score available to the public, we aim to facilitate further research in this area, encouraging the development of more culturally aware AI systems that respect and celebrate global diversity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_17475 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | How Culturally Aware are Vision-Language Models? Burda-Lassen, Olena Chadha, Aman Goswami, Shashank Jain, Vinija Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning An image is often considered worth a thousand words, and certain images can tell rich and insightful stories. Can these stories be told via image captioning? Images from folklore genres, such as mythology, folk dance, cultural signs, and symbols, are vital to every culture. Our research compares the performance of four popular vision-language models (GPT-4V, Gemini Pro Vision, LLaVA, and OpenFlamingo) in identifying culturally specific information in such images and creating accurate and culturally sensitive image captions. We also propose a new evaluation metric, the Cultural Awareness Score (CAS), which measures the degree of cultural awareness in image captions. We provide a dataset MOSAIC-1.5k labeled with ground truth for images containing cultural background and context and a labeled dataset with assigned Cultural Awareness Scores that can be used with unseen data. Creating culturally appropriate image captions is valuable for scientific research and can be beneficial for many practical applications. We envision our work will promote a deeper integration of cultural sensitivity in AI applications worldwide. By making the dataset and Cultural Awareness Score available to the public, we aim to facilitate further research in this area, encouraging the development of more culturally aware AI systems that respect and celebrate global diversity. |
| title | How Culturally Aware are Vision-Language Models? |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2405.17475 |