@inproceedings{zhibo-etal-2023-overcoming,
title = "Overcoming Language Priors with Counterfactual Inference for Visual Question Answering",
author = "Zhibo, Ren and
Huizhen, Wang and
Muhua, Zhu and
Yichao, Wang and
Tong, Xiao and
Jingbo, Zhu",
editor = "Sun, Maosong and
Qin, Bing and
Qiu, Xipeng and
Jiang, Jing and
Han, Xianpei",
booktitle = "Proceedings of the 22nd Chinese National Conference on Computational Linguistics",
month = aug,
year = "2023",
address = "Harbin, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2023.ccl-1.52",
pages = "600--610",
abstract = "{``}Recent years have seen a lot of efforts in attacking the issue of language priors in the field ofVisual Question Answering (VQA). Among the extensive efforts, causal inference is regarded asa promising direction to mitigate language bias by weakening the direct causal effect of questionson answers. In this paper, we follow the same direction and attack the issue of language priorsby incorporating counterfactual data. Moreover, we propose a two-stage training strategy whichis deemed to make better use of counterfactual data. Experiments on the widely used bench-mark VQA-CP v2 demonstrate the effectiveness of the proposed approach, which improves thebaseline by 21.21{\%} and outperforms most of the previous systems.{''}",
language = "English",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhibo-etal-2023-overcoming">
<titleInfo>
<title>Overcoming Language Priors with Counterfactual Inference for Visual Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ren</namePart>
<namePart type="family">Zhibo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wang</namePart>
<namePart type="family">Huizhen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhu</namePart>
<namePart type="family">Muhua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wang</namePart>
<namePart type="family">Yichao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Tong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhu</namePart>
<namePart type="family">Jingbo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xipeng</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianpei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Harbin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“Recent years have seen a lot of efforts in attacking the issue of language priors in the field ofVisual Question Answering (VQA). Among the extensive efforts, causal inference is regarded asa promising direction to mitigate language bias by weakening the direct causal effect of questionson answers. In this paper, we follow the same direction and attack the issue of language priorsby incorporating counterfactual data. Moreover, we propose a two-stage training strategy whichis deemed to make better use of counterfactual data. Experiments on the widely used bench-mark VQA-CP v2 demonstrate the effectiveness of the proposed approach, which improves thebaseline by 21.21% and outperforms most of the previous systems.”</abstract>
<identifier type="citekey">zhibo-etal-2023-overcoming</identifier>
<location>
<url>https://aclanthology.org/2023.ccl-1.52</url>
</location>
<part>
<date>2023-08</date>
<extent unit="page">
<start>600</start>
<end>610</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Overcoming Language Priors with Counterfactual Inference for Visual Question Answering
%A Zhibo, Ren
%A Huizhen, Wang
%A Muhua, Zhu
%A Yichao, Wang
%A Tong, Xiao
%A Jingbo, Zhu
%Y Sun, Maosong
%Y Qin, Bing
%Y Qiu, Xipeng
%Y Jiang, Jing
%Y Han, Xianpei
%S Proceedings of the 22nd Chinese National Conference on Computational Linguistics
%D 2023
%8 August
%I Chinese Information Processing Society of China
%C Harbin, China
%G English
%F zhibo-etal-2023-overcoming
%X “Recent years have seen a lot of efforts in attacking the issue of language priors in the field ofVisual Question Answering (VQA). Among the extensive efforts, causal inference is regarded asa promising direction to mitigate language bias by weakening the direct causal effect of questionson answers. In this paper, we follow the same direction and attack the issue of language priorsby incorporating counterfactual data. Moreover, we propose a two-stage training strategy whichis deemed to make better use of counterfactual data. Experiments on the widely used bench-mark VQA-CP v2 demonstrate the effectiveness of the proposed approach, which improves thebaseline by 21.21% and outperforms most of the previous systems.”
%U https://aclanthology.org/2023.ccl-1.52
%P 600-610
Markdown (Informal)
[Overcoming Language Priors with Counterfactual Inference for Visual Question Answering](https://aclanthology.org/2023.ccl-1.52) (Zhibo et al., CCL 2023)
ACL