@inproceedings{lin-etal-2023-fvqa,
title = "{FVQA} 2.0: Introducing Adversarial Samples into Fact-based Visual Question Answering",
author = "Lin, Weizhe and
Wang, Zhilin and
Byrne, Bill",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.11",
doi = "10.18653/v1/2023.findings-eacl.11",
pages = "149--157",
abstract = "The widely used Fact-based Visual Question Answering (FVQA) dataset contains visually-grounded questions that require information retrieval using common sense knowledge graphs to answer. It has been observed that the original dataset is highly imbalanced and concentrated on a small portion of its associated knowledge graph. We introduce FVQA 2.0 which contains adversarial variants of test questions to address this imbalance. We show that systems trained with the original FVQA train sets can be vulnerable to adversarial samples and we demonstrate an augmentation scheme to reduce this vulnerability without human annotations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2023-fvqa">
<titleInfo>
<title>FVQA 2.0: Introducing Adversarial Samples into Fact-based Visual Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weizhe</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhilin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bill</namePart>
<namePart type="family">Byrne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The widely used Fact-based Visual Question Answering (FVQA) dataset contains visually-grounded questions that require information retrieval using common sense knowledge graphs to answer. It has been observed that the original dataset is highly imbalanced and concentrated on a small portion of its associated knowledge graph. We introduce FVQA 2.0 which contains adversarial variants of test questions to address this imbalance. We show that systems trained with the original FVQA train sets can be vulnerable to adversarial samples and we demonstrate an augmentation scheme to reduce this vulnerability without human annotations.</abstract>
<identifier type="citekey">lin-etal-2023-fvqa</identifier>
<identifier type="doi">10.18653/v1/2023.findings-eacl.11</identifier>
<location>
<url>https://aclanthology.org/2023.findings-eacl.11</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>149</start>
<end>157</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FVQA 2.0: Introducing Adversarial Samples into Fact-based Visual Question Answering
%A Lin, Weizhe
%A Wang, Zhilin
%A Byrne, Bill
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F lin-etal-2023-fvqa
%X The widely used Fact-based Visual Question Answering (FVQA) dataset contains visually-grounded questions that require information retrieval using common sense knowledge graphs to answer. It has been observed that the original dataset is highly imbalanced and concentrated on a small portion of its associated knowledge graph. We introduce FVQA 2.0 which contains adversarial variants of test questions to address this imbalance. We show that systems trained with the original FVQA train sets can be vulnerable to adversarial samples and we demonstrate an augmentation scheme to reduce this vulnerability without human annotations.
%R 10.18653/v1/2023.findings-eacl.11
%U https://aclanthology.org/2023.findings-eacl.11
%U https://doi.org/10.18653/v1/2023.findings-eacl.11
%P 149-157
Markdown (Informal)
[FVQA 2.0: Introducing Adversarial Samples into Fact-based Visual Question Answering](https://aclanthology.org/2023.findings-eacl.11) (Lin et al., Findings 2023)
ACL