MLLMs-Augmented Visual-Language Representation Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911795566870528 |
|---|---|
| author | Liu, Yanqing Wang, Kai Shao, Wenqi Luo, Ping Qiao, Yu Shou, Mike Zheng Zhang, Kaipeng You, Yang |
| author_facet | Liu, Yanqing Wang, Kai Shao, Wenqi Luo, Ping Qiao, Yu Shou, Mike Zheng Zhang, Kaipeng You, Yang |
| contents | Visual-language pre-training has achieved remarkable success in many multi-modal tasks, largely attributed to the availability of large-scale image-text datasets. In this work, we demonstrate that Multi-modal Large Language Models (MLLMs) can enhance visual-language representation learning by establishing richer image-text associations for image-text datasets. Our approach is simple, utilizing MLLMs to extend multiple diverse captions for each image. To prevent the bias introduced by MLLMs' hallucinations and monotonous language styles, we propose "text shearing" to maintain the quality and availability of extended captions. In image-text retrieval, without introducing additional training cost, our method consistently obtains 5.6 ~ 35.0 and 16.8 ~ 46.1 improvement on Recall@1 under the fine-tuning and zero-shot settings, respectively. Notably, we obtain zero-shot results that are comparable to fine-tuning on target datasets, which encourages more exploration of the versatile use of MLLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_18765 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | MLLMs-Augmented Visual-Language Representation Learning Liu, Yanqing Wang, Kai Shao, Wenqi Luo, Ping Qiao, Yu Shou, Mike Zheng Zhang, Kaipeng You, Yang Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning Visual-language pre-training has achieved remarkable success in many multi-modal tasks, largely attributed to the availability of large-scale image-text datasets. In this work, we demonstrate that Multi-modal Large Language Models (MLLMs) can enhance visual-language representation learning by establishing richer image-text associations for image-text datasets. Our approach is simple, utilizing MLLMs to extend multiple diverse captions for each image. To prevent the bias introduced by MLLMs' hallucinations and monotonous language styles, we propose "text shearing" to maintain the quality and availability of extended captions. In image-text retrieval, without introducing additional training cost, our method consistently obtains 5.6 ~ 35.0 and 16.8 ~ 46.1 improvement on Recall@1 under the fine-tuning and zero-shot settings, respectively. Notably, we obtain zero-shot results that are comparable to fine-tuning on target datasets, which encourages more exploration of the versatile use of MLLMs. |
| title | MLLMs-Augmented Visual-Language Representation Learning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2311.18765 |