@inproceedings{jiang-etal-2023-vision,
title = "Vision Language Pre-training by Contrastive Learning with Cross-Modal Similarity Regulation",
author = "Jiang, Chaoya and
Ye, Wei and
Xu, Haiyang and
Huang, Songfang and
Huang, Fei and
Zhang, Shikun",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.819",
doi = "10.18653/v1/2023.acl-long.819",
pages = "14660--14679",
abstract = "In this paper, we reconsider the problem of (partial) false negative samples from the Mutual Information (MI) Maximization perspective, the traditional contrastive loss (like InfoNCE loss) will equally push away the anchor of all positive samples and negative samples regardless of their possible semantic similarities. We theoretically show that InfoNCE loss will not only maximize the MI between the anchor and positive samples but minimize the MI between the anchor and false negative samples even though they share similar semantic which could provide a possible theoretical explanation for the observation of the existence of false negative samples in the cross-modal contrastive learning will decrease the downstream task performance of VLP models. Above analysis motivate us to propose the VLP model with a novel Semantic Awared Contrastive Learning framework named SACL where different negative samples are assigned with different contrastive weights according to the semantic similarity between them and the anchor.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2023-vision">
<titleInfo>
<title>Vision Language Pre-training by Contrastive Learning with Cross-Modal Similarity Regulation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chaoya</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haiyang</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Songfang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shikun</namePart>
<namePart type="family">Zhang</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>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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>In this paper, we reconsider the problem of (partial) false negative samples from the Mutual Information (MI) Maximization perspective, the traditional contrastive loss (like InfoNCE loss) will equally push away the anchor of all positive samples and negative samples regardless of their possible semantic similarities. We theoretically show that InfoNCE loss will not only maximize the MI between the anchor and positive samples but minimize the MI between the anchor and false negative samples even though they share similar semantic which could provide a possible theoretical explanation for the observation of the existence of false negative samples in the cross-modal contrastive learning will decrease the downstream task performance of VLP models. Above analysis motivate us to propose the VLP model with a novel Semantic Awared Contrastive Learning framework named SACL where different negative samples are assigned with different contrastive weights according to the semantic similarity between them and the anchor.</abstract>
<identifier type="citekey">jiang-etal-2023-vision</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.819</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.819</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>14660</start>
<end>14679</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Vision Language Pre-training by Contrastive Learning with Cross-Modal Similarity Regulation
%A Jiang, Chaoya
%A Ye, Wei
%A Xu, Haiyang
%A Huang, Songfang
%A Huang, Fei
%A Zhang, Shikun
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F jiang-etal-2023-vision
%X In this paper, we reconsider the problem of (partial) false negative samples from the Mutual Information (MI) Maximization perspective, the traditional contrastive loss (like InfoNCE loss) will equally push away the anchor of all positive samples and negative samples regardless of their possible semantic similarities. We theoretically show that InfoNCE loss will not only maximize the MI between the anchor and positive samples but minimize the MI between the anchor and false negative samples even though they share similar semantic which could provide a possible theoretical explanation for the observation of the existence of false negative samples in the cross-modal contrastive learning will decrease the downstream task performance of VLP models. Above analysis motivate us to propose the VLP model with a novel Semantic Awared Contrastive Learning framework named SACL where different negative samples are assigned with different contrastive weights according to the semantic similarity between them and the anchor.
%R 10.18653/v1/2023.acl-long.819
%U https://aclanthology.org/2023.acl-long.819
%U https://doi.org/10.18653/v1/2023.acl-long.819
%P 14660-14679
Markdown (Informal)
[Vision Language Pre-training by Contrastive Learning with Cross-Modal Similarity Regulation](https://aclanthology.org/2023.acl-long.819) (Jiang et al., ACL 2023)
ACL