@inproceedings{zhang-etal-2023-grounding,
title = "Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?",
author = "Zhang, Yichi and
Pan, Jiayi and
Zhou, Yuchen and
Pan, Rui and
Chai, Joyce",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.348/",
doi = "10.18653/v1/2023.emnlp-main.348",
pages = "5718--5728",
abstract = "Vision-Language Models (VLMs) are trained on vast amounts of data captured by humans emulating our understanding of the world. However, known as visual illusions, human`s perception of reality isn`t always faithful to the physical world. This raises a key question: do VLMs have the similar kind of illusions as humans do, or do they faithfully learn to represent reality? To investigate this question, we build a dataset containing five types of visual illusions and formulate four tasks to examine visual illusions in state-of-the-art VLMs. Our findings have shown that although the overall alignment is low, larger models are closer to human perception and more susceptible to visual illusions. Our dataset and initial findings will promote a better understanding of visual illusions in humans and machines and provide a stepping stone for future computational models that can better align humans and machines in perceiving and communicating about the shared visual world. The code and data are available at [github.com/vl-illusion/dataset](https://github.com/vl-illusion/dataset)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2023-grounding">
<titleInfo>
<title>Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yichi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiayi</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuchen</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Vision-Language Models (VLMs) are trained on vast amounts of data captured by humans emulating our understanding of the world. However, known as visual illusions, human‘s perception of reality isn‘t always faithful to the physical world. This raises a key question: do VLMs have the similar kind of illusions as humans do, or do they faithfully learn to represent reality? To investigate this question, we build a dataset containing five types of visual illusions and formulate four tasks to examine visual illusions in state-of-the-art VLMs. Our findings have shown that although the overall alignment is low, larger models are closer to human perception and more susceptible to visual illusions. Our dataset and initial findings will promote a better understanding of visual illusions in humans and machines and provide a stepping stone for future computational models that can better align humans and machines in perceiving and communicating about the shared visual world. The code and data are available at [github.com/vl-illusion/dataset](https://github.com/vl-illusion/dataset).</abstract>
<identifier type="citekey">zhang-etal-2023-grounding</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.348</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.348/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>5718</start>
<end>5728</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?
%A Zhang, Yichi
%A Pan, Jiayi
%A Zhou, Yuchen
%A Pan, Rui
%A Chai, Joyce
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhang-etal-2023-grounding
%X Vision-Language Models (VLMs) are trained on vast amounts of data captured by humans emulating our understanding of the world. However, known as visual illusions, human‘s perception of reality isn‘t always faithful to the physical world. This raises a key question: do VLMs have the similar kind of illusions as humans do, or do they faithfully learn to represent reality? To investigate this question, we build a dataset containing five types of visual illusions and formulate four tasks to examine visual illusions in state-of-the-art VLMs. Our findings have shown that although the overall alignment is low, larger models are closer to human perception and more susceptible to visual illusions. Our dataset and initial findings will promote a better understanding of visual illusions in humans and machines and provide a stepping stone for future computational models that can better align humans and machines in perceiving and communicating about the shared visual world. The code and data are available at [github.com/vl-illusion/dataset](https://github.com/vl-illusion/dataset).
%R 10.18653/v1/2023.emnlp-main.348
%U https://aclanthology.org/2023.emnlp-main.348/
%U https://doi.org/10.18653/v1/2023.emnlp-main.348
%P 5718-5728
Markdown (Informal)
[Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?](https://aclanthology.org/2023.emnlp-main.348/) (Zhang et al., EMNLP 2023)
ACL