@inproceedings{li-etal-2024-localization,
title = "Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models",
author = "Li, Zhuowan and
Xie, Cihang and
Van Durme, Benjamin and
Yuille, Alan",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-long.146/",
pages = "2378--2390",
abstract = "Despite the impressive advancements achieved through vision-and-language pretraining, it remains unclear whether multi-modal learning can help understand each individual modality. In this work, we conduct a comparative analysis of the visual representations in existing vision-and-language models and vision-only models by probing on a broad range of tasks. Five probing tasks are evaluated in order to assess the quality of the learned representations in a nuanced manner. Our results on five probing tasks suggest vision-and-language models are better at label prediction tasks like object and attribute prediction, while vision-only models are stronger at dense prediction tasks that require more localized information. We hope our study sheds light on the role of language in visual learning, and serves as an empirical guide for various pretrained models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2024-localization">
<titleInfo>
<title>Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhuowan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cihang</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Van Durme</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Yuille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Despite the impressive advancements achieved through vision-and-language pretraining, it remains unclear whether multi-modal learning can help understand each individual modality. In this work, we conduct a comparative analysis of the visual representations in existing vision-and-language models and vision-only models by probing on a broad range of tasks. Five probing tasks are evaluated in order to assess the quality of the learned representations in a nuanced manner. Our results on five probing tasks suggest vision-and-language models are better at label prediction tasks like object and attribute prediction, while vision-only models are stronger at dense prediction tasks that require more localized information. We hope our study sheds light on the role of language in visual learning, and serves as an empirical guide for various pretrained models.</abstract>
<identifier type="citekey">li-etal-2024-localization</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-long.146/</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>2378</start>
<end>2390</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models
%A Li, Zhuowan
%A Xie, Cihang
%A Van Durme, Benjamin
%A Yuille, Alan
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F li-etal-2024-localization
%X Despite the impressive advancements achieved through vision-and-language pretraining, it remains unclear whether multi-modal learning can help understand each individual modality. In this work, we conduct a comparative analysis of the visual representations in existing vision-and-language models and vision-only models by probing on a broad range of tasks. Five probing tasks are evaluated in order to assess the quality of the learned representations in a nuanced manner. Our results on five probing tasks suggest vision-and-language models are better at label prediction tasks like object and attribute prediction, while vision-only models are stronger at dense prediction tasks that require more localized information. We hope our study sheds light on the role of language in visual learning, and serves as an empirical guide for various pretrained models.
%U https://aclanthology.org/2024.eacl-long.146/
%P 2378-2390
Markdown (Informal)
[Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models](https://aclanthology.org/2024.eacl-long.146/) (Li et al., EACL 2024)
ACL