@inproceedings{sun-etal-2023-fusion,
title = "Fusion or Defusion? Flexible Vision-and-Language Pre-Training",
author = "Sun, Rongyi and
Li, Ziran and
Ding, Yifeng and
Wang, Qifan and
Wang, Jingang and
Zheng, Haitao and
Wu, Wei and
Xian, Yunsen",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.316/",
doi = "10.18653/v1/2023.findings-acl.316",
pages = "5105--5119",
abstract = "Existing approaches in the vision-and-language pre-training (VLP) paradigm mainly deploy either fusion-based encoders or dual-encoders, failing to achieve both effectiveness and efficiency in downstream multimodal tasks. In this paper, we build a flexible VLP model by incorporating cross-modal fusions into a dual-encoder architecture, where the introduced fusion modules can be easily decoupled from the dual encoder so as to switch the model to a fusion-free one. To better absorb cross-modal features from the fusion modules, we design a cross-modal knowledge transfer strategy along with other comprehensive pre-training tasks to guide the training process, which can further strengthen both the fusion-based and fusion-free representation learning. Extensive experiments conducted on various downstream vision-language tasks show that our proposed model is well-equipped with effectiveness as well as efficiency, demonstrating a superior performance compared with other strong VLP models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2023-fusion">
<titleInfo>
<title>Fusion or Defusion? Flexible Vision-and-Language Pre-Training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rongyi</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziran</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifeng</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qifan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haitao</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunsen</namePart>
<namePart type="family">Xian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing approaches in the vision-and-language pre-training (VLP) paradigm mainly deploy either fusion-based encoders or dual-encoders, failing to achieve both effectiveness and efficiency in downstream multimodal tasks. In this paper, we build a flexible VLP model by incorporating cross-modal fusions into a dual-encoder architecture, where the introduced fusion modules can be easily decoupled from the dual encoder so as to switch the model to a fusion-free one. To better absorb cross-modal features from the fusion modules, we design a cross-modal knowledge transfer strategy along with other comprehensive pre-training tasks to guide the training process, which can further strengthen both the fusion-based and fusion-free representation learning. Extensive experiments conducted on various downstream vision-language tasks show that our proposed model is well-equipped with effectiveness as well as efficiency, demonstrating a superior performance compared with other strong VLP models.</abstract>
<identifier type="citekey">sun-etal-2023-fusion</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.316</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.316/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>5105</start>
<end>5119</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fusion or Defusion? Flexible Vision-and-Language Pre-Training
%A Sun, Rongyi
%A Li, Ziran
%A Ding, Yifeng
%A Wang, Qifan
%A Wang, Jingang
%A Zheng, Haitao
%A Wu, Wei
%A Xian, Yunsen
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F sun-etal-2023-fusion
%X Existing approaches in the vision-and-language pre-training (VLP) paradigm mainly deploy either fusion-based encoders or dual-encoders, failing to achieve both effectiveness and efficiency in downstream multimodal tasks. In this paper, we build a flexible VLP model by incorporating cross-modal fusions into a dual-encoder architecture, where the introduced fusion modules can be easily decoupled from the dual encoder so as to switch the model to a fusion-free one. To better absorb cross-modal features from the fusion modules, we design a cross-modal knowledge transfer strategy along with other comprehensive pre-training tasks to guide the training process, which can further strengthen both the fusion-based and fusion-free representation learning. Extensive experiments conducted on various downstream vision-language tasks show that our proposed model is well-equipped with effectiveness as well as efficiency, demonstrating a superior performance compared with other strong VLP models.
%R 10.18653/v1/2023.findings-acl.316
%U https://aclanthology.org/2023.findings-acl.316/
%U https://doi.org/10.18653/v1/2023.findings-acl.316
%P 5105-5119
Markdown (Informal)
[Fusion or Defusion? Flexible Vision-and-Language Pre-Training](https://aclanthology.org/2023.findings-acl.316/) (Sun et al., Findings 2023)
ACL
- Rongyi Sun, Ziran Li, Yifeng Ding, Qifan Wang, Jingang Wang, Haitao Zheng, Wei Wu, and Yunsen Xian. 2023. Fusion or Defusion? Flexible Vision-and-Language Pre-Training. In Findings of the Association for Computational Linguistics: ACL 2023, pages 5105–5119, Toronto, Canada. Association for Computational Linguistics.