Saved in:
Bibliographic Details
Main Authors: Zhang, Xinyun, Tan, Haochen, Wu, Han, Yu, Bei
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2305.07358
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913235360284672
author Zhang, Xinyun
Tan, Haochen
Wu, Han
Yu, Bei
author_facet Zhang, Xinyun
Tan, Haochen
Wu, Han
Yu, Bei
contents Humans learn language via multi-modal knowledge. However, due to the text-only pre-training scheme, most existing pre-trained language models (PLMs) are hindered from the multi-modal information. To inject visual knowledge into PLMs, existing methods incorporate either the text or image encoder of vision-language models (VLMs) to encode the visual information and update all the original parameters of PLMs for knowledge fusion. In this paper, we propose a new plug-and-play module, X-adapter, to flexibly leverage the aligned visual and textual knowledge learned in pre-trained VLMs and efficiently inject them into PLMs. Specifically, we insert X-adapters into PLMs, and only the added parameters are updated during adaptation. To fully exploit the potential in VLMs, X-adapters consist of two sub-modules, V-expert and T-expert, to fuse VLMs' image and text representations, respectively. We can opt for activating different sub-modules depending on the downstream tasks. Experimental results show that our method can significantly improve the performance on object-color reasoning and natural language understanding (NLU) tasks compared with PLM baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2305_07358
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Towards Versatile and Efficient Visual Knowledge Integration into Pre-trained Language Models with Cross-Modal Adapters
Zhang, Xinyun
Tan, Haochen
Wu, Han
Yu, Bei
Computation and Language
Humans learn language via multi-modal knowledge. However, due to the text-only pre-training scheme, most existing pre-trained language models (PLMs) are hindered from the multi-modal information. To inject visual knowledge into PLMs, existing methods incorporate either the text or image encoder of vision-language models (VLMs) to encode the visual information and update all the original parameters of PLMs for knowledge fusion. In this paper, we propose a new plug-and-play module, X-adapter, to flexibly leverage the aligned visual and textual knowledge learned in pre-trained VLMs and efficiently inject them into PLMs. Specifically, we insert X-adapters into PLMs, and only the added parameters are updated during adaptation. To fully exploit the potential in VLMs, X-adapters consist of two sub-modules, V-expert and T-expert, to fuse VLMs' image and text representations, respectively. We can opt for activating different sub-modules depending on the downstream tasks. Experimental results show that our method can significantly improve the performance on object-color reasoning and natural language understanding (NLU) tasks compared with PLM baselines.
title Towards Versatile and Efficient Visual Knowledge Integration into Pre-trained Language Models with Cross-Modal Adapters
topic Computation and Language
url https://arxiv.org/abs/2305.07358