Rebalanced Vision-Language Retrieval Considering Structure-Aware Distillation
Vision-language retrieval aims to search for similar instances in one modality based on queries from another modality. The primary objective is to learn cross-modal matching representations in a latent common space. Actually, the assumption underlying cross-modal matching is modal balance, where eac...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2024-12 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Yang, Yang Xi, Wenjuan Zhou, Luping Tang, Jinhui |
description | Vision-language retrieval aims to search for similar instances in one modality based on queries from another modality. The primary objective is to learn cross-modal matching representations in a latent common space. Actually, the assumption underlying cross-modal matching is modal balance, where each modality contains sufficient information to represent the others. However, noise interference and modality insufficiency often lead to modal imbalance, making it a common phenomenon in practice. The impact of imbalance on retrieval performance remains an open question. In this paper, we first demonstrate that ultimate cross-modal matching is generally sub-optimal for cross-modal retrieval when imbalanced modalities exist. The structure of instances in the common space is inherently influenced when facing imbalanced modalities, posing a challenge to cross-modal similarity measurement. To address this issue, we emphasize the importance of meaningful structure-preserved matching. Accordingly, we propose a simple yet effective method to rebalance cross-modal matching by learning structure-preserved matching representations. Specifically, we design a novel multi-granularity cross-modal matching that incorporates structure-aware distillation alongside the cross-modal matching loss. While the cross-modal matching loss constraints instance-level matching, the structure-aware distillation further regularizes the geometric consistency between learned matching representations and intra-modal representations through the developed relational matching. Extensive experiments on different datasets affirm the superior cross-modal retrieval performance of our approach, simultaneously enhancing single-modal retrieval capabilities compared to the baseline models. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3145902624</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3145902624</sourcerecordid><originalsourceid>FETCH-proquest_journals_31459026243</originalsourceid><addsrcrecordid>eNqNjr0KwjAURoMgWLTvEHAOtEnrzyhVcdBFxbVc22tJCYnmJvr6dvABnL7hnAPfiCVSqVysCiknLCXqsyyTi6UsS5Ww0xnvYMA22PKbJu2sOILtInTIzxi8xjcYXjlLukWvbccvwccmRI9i8wGPfKspaGMgDO2MjR9gCNPfTtl8v7tWB_H07hWRQt276O2AapUX5Xr4IQv1n_UF0fs-ZQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3145902624</pqid></control><display><type>article</type><title>Rebalanced Vision-Language Retrieval Considering Structure-Aware Distillation</title><source>Free E- Journals</source><creator>Yang, Yang ; Xi, Wenjuan ; Zhou, Luping ; Tang, Jinhui</creator><creatorcontrib>Yang, Yang ; Xi, Wenjuan ; Zhou, Luping ; Tang, Jinhui</creatorcontrib><description>Vision-language retrieval aims to search for similar instances in one modality based on queries from another modality. The primary objective is to learn cross-modal matching representations in a latent common space. Actually, the assumption underlying cross-modal matching is modal balance, where each modality contains sufficient information to represent the others. However, noise interference and modality insufficiency often lead to modal imbalance, making it a common phenomenon in practice. The impact of imbalance on retrieval performance remains an open question. In this paper, we first demonstrate that ultimate cross-modal matching is generally sub-optimal for cross-modal retrieval when imbalanced modalities exist. The structure of instances in the common space is inherently influenced when facing imbalanced modalities, posing a challenge to cross-modal similarity measurement. To address this issue, we emphasize the importance of meaningful structure-preserved matching. Accordingly, we propose a simple yet effective method to rebalance cross-modal matching by learning structure-preserved matching representations. Specifically, we design a novel multi-granularity cross-modal matching that incorporates structure-aware distillation alongside the cross-modal matching loss. While the cross-modal matching loss constraints instance-level matching, the structure-aware distillation further regularizes the geometric consistency between learned matching representations and intra-modal representations through the developed relational matching. Extensive experiments on different datasets affirm the superior cross-modal retrieval performance of our approach, simultaneously enhancing single-modal retrieval capabilities compared to the baseline models.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Matching ; Representations ; Retrieval</subject><ispartof>arXiv.org, 2024-12</ispartof><rights>2024. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Yang, Yang</creatorcontrib><creatorcontrib>Xi, Wenjuan</creatorcontrib><creatorcontrib>Zhou, Luping</creatorcontrib><creatorcontrib>Tang, Jinhui</creatorcontrib><title>Rebalanced Vision-Language Retrieval Considering Structure-Aware Distillation</title><title>arXiv.org</title><description>Vision-language retrieval aims to search for similar instances in one modality based on queries from another modality. The primary objective is to learn cross-modal matching representations in a latent common space. Actually, the assumption underlying cross-modal matching is modal balance, where each modality contains sufficient information to represent the others. However, noise interference and modality insufficiency often lead to modal imbalance, making it a common phenomenon in practice. The impact of imbalance on retrieval performance remains an open question. In this paper, we first demonstrate that ultimate cross-modal matching is generally sub-optimal for cross-modal retrieval when imbalanced modalities exist. The structure of instances in the common space is inherently influenced when facing imbalanced modalities, posing a challenge to cross-modal similarity measurement. To address this issue, we emphasize the importance of meaningful structure-preserved matching. Accordingly, we propose a simple yet effective method to rebalance cross-modal matching by learning structure-preserved matching representations. Specifically, we design a novel multi-granularity cross-modal matching that incorporates structure-aware distillation alongside the cross-modal matching loss. While the cross-modal matching loss constraints instance-level matching, the structure-aware distillation further regularizes the geometric consistency between learned matching representations and intra-modal representations through the developed relational matching. Extensive experiments on different datasets affirm the superior cross-modal retrieval performance of our approach, simultaneously enhancing single-modal retrieval capabilities compared to the baseline models.</description><subject>Matching</subject><subject>Representations</subject><subject>Retrieval</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNjr0KwjAURoMgWLTvEHAOtEnrzyhVcdBFxbVc22tJCYnmJvr6dvABnL7hnAPfiCVSqVysCiknLCXqsyyTi6UsS5Ww0xnvYMA22PKbJu2sOILtInTIzxi8xjcYXjlLukWvbccvwccmRI9i8wGPfKspaGMgDO2MjR9gCNPfTtl8v7tWB_H07hWRQt276O2AapUX5Xr4IQv1n_UF0fs-ZQ</recordid><startdate>20241214</startdate><enddate>20241214</enddate><creator>Yang, Yang</creator><creator>Xi, Wenjuan</creator><creator>Zhou, Luping</creator><creator>Tang, Jinhui</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20241214</creationdate><title>Rebalanced Vision-Language Retrieval Considering Structure-Aware Distillation</title><author>Yang, Yang ; Xi, Wenjuan ; Zhou, Luping ; Tang, Jinhui</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_31459026243</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Matching</topic><topic>Representations</topic><topic>Retrieval</topic><toplevel>online_resources</toplevel><creatorcontrib>Yang, Yang</creatorcontrib><creatorcontrib>Xi, Wenjuan</creatorcontrib><creatorcontrib>Zhou, Luping</creatorcontrib><creatorcontrib>Tang, Jinhui</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yang, Yang</au><au>Xi, Wenjuan</au><au>Zhou, Luping</au><au>Tang, Jinhui</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Rebalanced Vision-Language Retrieval Considering Structure-Aware Distillation</atitle><jtitle>arXiv.org</jtitle><date>2024-12-14</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Vision-language retrieval aims to search for similar instances in one modality based on queries from another modality. The primary objective is to learn cross-modal matching representations in a latent common space. Actually, the assumption underlying cross-modal matching is modal balance, where each modality contains sufficient information to represent the others. However, noise interference and modality insufficiency often lead to modal imbalance, making it a common phenomenon in practice. The impact of imbalance on retrieval performance remains an open question. In this paper, we first demonstrate that ultimate cross-modal matching is generally sub-optimal for cross-modal retrieval when imbalanced modalities exist. The structure of instances in the common space is inherently influenced when facing imbalanced modalities, posing a challenge to cross-modal similarity measurement. To address this issue, we emphasize the importance of meaningful structure-preserved matching. Accordingly, we propose a simple yet effective method to rebalance cross-modal matching by learning structure-preserved matching representations. Specifically, we design a novel multi-granularity cross-modal matching that incorporates structure-aware distillation alongside the cross-modal matching loss. While the cross-modal matching loss constraints instance-level matching, the structure-aware distillation further regularizes the geometric consistency between learned matching representations and intra-modal representations through the developed relational matching. Extensive experiments on different datasets affirm the superior cross-modal retrieval performance of our approach, simultaneously enhancing single-modal retrieval capabilities compared to the baseline models.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2024-12 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_3145902624 |
source | Free E- Journals |
subjects | Matching Representations Retrieval |
title | Rebalanced Vision-Language Retrieval Considering Structure-Aware Distillation |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T09%3A49%3A09IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Rebalanced%20Vision-Language%20Retrieval%20Considering%20Structure-Aware%20Distillation&rft.jtitle=arXiv.org&rft.au=Yang,%20Yang&rft.date=2024-12-14&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3145902624%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3145902624&rft_id=info:pmid/&rfr_iscdi=true |