VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval

Junjie Zhou, Zheng Liu, Shitao Xiao, Bo Zhao, Yongping Xiong


Abstract
Multi-modal retrieval becomes increasingly popular in practice. However, the existing retrievers are mostly text-oriented, which lack the capability to process visual information. Despite the presence of vision-language models like CLIP, the current methods are severely limited in representing the text-only and image-only data. In this work, we present a new embedding model VISTA for universal multi-modal retrieval. Our work brings forth threefold technical contributions. Firstly, we introduce a flexible architecture which extends a powerful text encoder with the image understanding capability by introducing visual token embeddings. Secondly, we develop two data generation strategies, which bring high-quality composed image-text to facilitate the training of the embedding model. Thirdly, we introduce a multi-stage training algorithm, which first aligns the visual token embedding with the text encoder using massive weakly labeled data, and then develops multi-modal representation capability using the generated composed image-text data. In our experiments, VISTA achieves superior performances across a variety of multi-modal retrieval tasks in both zero-shot and supervised settings. Our model, data, and source code are available at https://github.com/FlagOpen/FlagEmbedding.
Anthology ID:
2024.acl-long.175
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3185–3200
Language:
URL:
https://aclanthology.org/2024.acl-long.175
DOI:
10.18653/v1/2024.acl-long.175
Bibkey:
Cite (ACL):
Junjie Zhou, Zheng Liu, Shitao Xiao, Bo Zhao, and Yongping Xiong. 2024. VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3185–3200, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval (Zhou et al., ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2024.acl-long.175.pdf