UNIMO-2: End-to-End Unified Vision-Language Grounded Learning

Wei Li, Can Gao, Guocheng Niu, Xinyan Xiao, Hao Liu, Jiachen Liu, Hua Wu, Haifeng Wang


Abstract
Vision-Language Pre-training (VLP) has achieved impressive performance on various cross-modal downstream tasks. However, most existing methods can only learn from aligned image-caption data and rely heavily on expensive regional features, which greatly limits their scalability and performance. In this paper, we propose an end-to-end unified-modal pre-training framework, namely UNIMO-2, for joint learning on both aligned image-caption data and unaligned image-only and text-only corpus. We build a unified Transformer model to jointly learn visual representations, textual representations and semantic alignment between images and texts. In particular, we propose to conduct grounded learning on both images and texts via a sharing grounded space, which helps bridge unaligned images and texts, and align the visual and textual semantic spaces on different types of corpora. The experiments show that our grounded learning method can improve textual and visual semantic alignment for improving performance on various cross-modal tasks. Moreover, benefiting from effective joint modeling of different types of corpora, our model also achieves impressive performance on single-modal visual and textual tasks. Our code and models are public at the UNIMO project page https://unimo-ptm.github.io/.
Anthology ID:
2022.findings-acl.251
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3187–3201
Language:
URL:
https://aclanthology.org/2022.findings-acl.251
DOI:
10.18653/v1/2022.findings-acl.251
Bibkey:
Cite (ACL):
Wei Li, Can Gao, Guocheng Niu, Xinyan Xiao, Hao Liu, Jiachen Liu, Hua Wu, and Haifeng Wang. 2022. UNIMO-2: End-to-End Unified Vision-Language Grounded Learning. In Findings of the Association for Computational Linguistics: ACL 2022, pages 3187–3201, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
UNIMO-2: End-to-End Unified Vision-Language Grounded Learning (Li et al., Findings 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2022.findings-acl.251.pdf
Code
 PaddlePaddle/Research
Data
ImageNetMS COCOMultiNLISNLI-VESSTSST-2Visual Genome