Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916131256664064 |
|---|---|
| author | Lei, Xuanyu Yang, Zonghan Chen, Xinrui Li, Peng Liu, Yang |
| author_facet | Lei, Xuanyu Yang, Zonghan Chen, Xinrui Li, Peng Liu, Yang |
| contents | State-of-the-art Large Multi-Modal Models (LMMs) have demonstrated exceptional capabilities in vision-language tasks. Despite their advanced functionalities, the performances of LMMs are still limited in challenging scenarios that require complex reasoning with multiple levels of visual information. Existing prompting techniques for LMMs focus on either improving textual reasoning or leveraging tools for image preprocessing, lacking a simple and general visual prompting scheme to promote vision-language coordination in LMMs. In this work, we propose Scaffold prompting that scaffolds coordinates to promote vision-language coordination. Specifically, Scaffold overlays a dot matrix within the image as visual information anchors and leverages multi-dimensional coordinates as textual positional references. Extensive experiments on a wide range of challenging vision-language tasks demonstrate the superiority of Scaffold over GPT-4V with the textual CoT prompting. Our code is released in https://github.com/leixy20/Scaffold. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_12058 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models Lei, Xuanyu Yang, Zonghan Chen, Xinrui Li, Peng Liu, Yang Computer Vision and Pattern Recognition Computation and Language State-of-the-art Large Multi-Modal Models (LMMs) have demonstrated exceptional capabilities in vision-language tasks. Despite their advanced functionalities, the performances of LMMs are still limited in challenging scenarios that require complex reasoning with multiple levels of visual information. Existing prompting techniques for LMMs focus on either improving textual reasoning or leveraging tools for image preprocessing, lacking a simple and general visual prompting scheme to promote vision-language coordination in LMMs. In this work, we propose Scaffold prompting that scaffolds coordinates to promote vision-language coordination. Specifically, Scaffold overlays a dot matrix within the image as visual information anchors and leverages multi-dimensional coordinates as textual positional references. Extensive experiments on a wide range of challenging vision-language tasks demonstrate the superiority of Scaffold over GPT-4V with the textual CoT prompting. Our code is released in https://github.com/leixy20/Scaffold. |
| title | Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2402.12058 |