Cross-modal Zero-shot Hashing

Hashing has been widely studied for big data retrieval due to its low storage cost and fast query speed. Zero-shot hashing (ZSH) aims to learn a hashing model that is trained using only samples from seen categories, but can generalize well to samples of unseen categories. ZSH generally uses category...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Xuanwu, Li, Zhao, Wang, Jun, Yu, Guoxian, Domeniconi, Carlotta, Zhang, Xiangliang
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Liu, Xuanwu
Li, Zhao
Wang, Jun
Yu, Guoxian
Domeniconi, Carlotta
Zhang, Xiangliang
description Hashing has been widely studied for big data retrieval due to its low storage cost and fast query speed. Zero-shot hashing (ZSH) aims to learn a hashing model that is trained using only samples from seen categories, but can generalize well to samples of unseen categories. ZSH generally uses category attributes to seek a semantic embedding space to transfer knowledge from seen categories to unseen ones. As a result, it may perform poorly when labeled data are insufficient. ZSH methods are mainly designed for single-modality data, which prevents their application to the widely spread multi-modal data. On the other hand, existing cross-modal hashing solutions assume that all the modalities share the same category labels, while in practice the labels of different data modalities may be different. To address these issues, we propose a general Cross-modal Zero-shot Hashing (CZHash) solution to effectively leverage unlabeled and labeled multi-modality data with different label spaces. CZHash first quantifies the composite similarity between instances using label and feature information. It then defines an objective function to achieve deep feature learning compatible with the composite similarity preserving, category attribute space learning, and hashing coding function learning. CZHash further introduces an alternative optimization procedure to jointly optimize these learning objectives. Experiments on benchmark multi-modal datasets show that CZHash significantly outperforms related representative hashing approaches both on effectiveness and adaptability.
doi_str_mv 10.48550/arxiv.1908.07388
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1908_07388</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1908_07388</sourcerecordid><originalsourceid>FETCH-LOGICAL-a678-361b41caa02143fc9ad52f88ea7b1b363a4688e4da3236f53c83a24adb37e4013</originalsourceid><addsrcrecordid>eNotzr0OgjAYheEuDga9AAcjN1Bs-UpbRkNUTExcmFzIx0-FBMS0xujdq-h08i4nDyELzgKho4it0T7bR8BjpgOmQOspWSZ2cI72Q4Wdf67tQF0z3P0UXdNeLzMyMdi5ev5fj2S7bZak9HjaH5LNkaJUmoLkheAlIgu5AFPGWEWh0bpGVfACJKCQnxIVQgjSRFBqwFBgVYCqBePgkdXvdvTlN9v2aF_515mPTngDrdQ2dg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Cross-modal Zero-shot Hashing</title><source>arXiv.org</source><creator>Liu, Xuanwu ; Li, Zhao ; Wang, Jun ; Yu, Guoxian ; Domeniconi, Carlotta ; Zhang, Xiangliang</creator><creatorcontrib>Liu, Xuanwu ; Li, Zhao ; Wang, Jun ; Yu, Guoxian ; Domeniconi, Carlotta ; Zhang, Xiangliang</creatorcontrib><description>Hashing has been widely studied for big data retrieval due to its low storage cost and fast query speed. Zero-shot hashing (ZSH) aims to learn a hashing model that is trained using only samples from seen categories, but can generalize well to samples of unseen categories. ZSH generally uses category attributes to seek a semantic embedding space to transfer knowledge from seen categories to unseen ones. As a result, it may perform poorly when labeled data are insufficient. ZSH methods are mainly designed for single-modality data, which prevents their application to the widely spread multi-modal data. On the other hand, existing cross-modal hashing solutions assume that all the modalities share the same category labels, while in practice the labels of different data modalities may be different. To address these issues, we propose a general Cross-modal Zero-shot Hashing (CZHash) solution to effectively leverage unlabeled and labeled multi-modality data with different label spaces. CZHash first quantifies the composite similarity between instances using label and feature information. It then defines an objective function to achieve deep feature learning compatible with the composite similarity preserving, category attribute space learning, and hashing coding function learning. CZHash further introduces an alternative optimization procedure to jointly optimize these learning objectives. Experiments on benchmark multi-modal datasets show that CZHash significantly outperforms related representative hashing approaches both on effectiveness and adaptability.</description><identifier>DOI: 10.48550/arxiv.1908.07388</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Learning</subject><creationdate>2019-08</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1908.07388$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1908.07388$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Liu, Xuanwu</creatorcontrib><creatorcontrib>Li, Zhao</creatorcontrib><creatorcontrib>Wang, Jun</creatorcontrib><creatorcontrib>Yu, Guoxian</creatorcontrib><creatorcontrib>Domeniconi, Carlotta</creatorcontrib><creatorcontrib>Zhang, Xiangliang</creatorcontrib><title>Cross-modal Zero-shot Hashing</title><description>Hashing has been widely studied for big data retrieval due to its low storage cost and fast query speed. Zero-shot hashing (ZSH) aims to learn a hashing model that is trained using only samples from seen categories, but can generalize well to samples of unseen categories. ZSH generally uses category attributes to seek a semantic embedding space to transfer knowledge from seen categories to unseen ones. As a result, it may perform poorly when labeled data are insufficient. ZSH methods are mainly designed for single-modality data, which prevents their application to the widely spread multi-modal data. On the other hand, existing cross-modal hashing solutions assume that all the modalities share the same category labels, while in practice the labels of different data modalities may be different. To address these issues, we propose a general Cross-modal Zero-shot Hashing (CZHash) solution to effectively leverage unlabeled and labeled multi-modality data with different label spaces. CZHash first quantifies the composite similarity between instances using label and feature information. It then defines an objective function to achieve deep feature learning compatible with the composite similarity preserving, category attribute space learning, and hashing coding function learning. CZHash further introduces an alternative optimization procedure to jointly optimize these learning objectives. Experiments on benchmark multi-modal datasets show that CZHash significantly outperforms related representative hashing approaches both on effectiveness and adaptability.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzr0OgjAYheEuDga9AAcjN1Bs-UpbRkNUTExcmFzIx0-FBMS0xujdq-h08i4nDyELzgKho4it0T7bR8BjpgOmQOspWSZ2cI72Q4Wdf67tQF0z3P0UXdNeLzMyMdi5ev5fj2S7bZak9HjaH5LNkaJUmoLkheAlIgu5AFPGWEWh0bpGVfACJKCQnxIVQgjSRFBqwFBgVYCqBePgkdXvdvTlN9v2aF_515mPTngDrdQ2dg</recordid><startdate>20190819</startdate><enddate>20190819</enddate><creator>Liu, Xuanwu</creator><creator>Li, Zhao</creator><creator>Wang, Jun</creator><creator>Yu, Guoxian</creator><creator>Domeniconi, Carlotta</creator><creator>Zhang, Xiangliang</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20190819</creationdate><title>Cross-modal Zero-shot Hashing</title><author>Liu, Xuanwu ; Li, Zhao ; Wang, Jun ; Yu, Guoxian ; Domeniconi, Carlotta ; Zhang, Xiangliang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a678-361b41caa02143fc9ad52f88ea7b1b363a4688e4da3236f53c83a24adb37e4013</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Liu, Xuanwu</creatorcontrib><creatorcontrib>Li, Zhao</creatorcontrib><creatorcontrib>Wang, Jun</creatorcontrib><creatorcontrib>Yu, Guoxian</creatorcontrib><creatorcontrib>Domeniconi, Carlotta</creatorcontrib><creatorcontrib>Zhang, Xiangliang</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Liu, Xuanwu</au><au>Li, Zhao</au><au>Wang, Jun</au><au>Yu, Guoxian</au><au>Domeniconi, Carlotta</au><au>Zhang, Xiangliang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Cross-modal Zero-shot Hashing</atitle><date>2019-08-19</date><risdate>2019</risdate><abstract>Hashing has been widely studied for big data retrieval due to its low storage cost and fast query speed. Zero-shot hashing (ZSH) aims to learn a hashing model that is trained using only samples from seen categories, but can generalize well to samples of unseen categories. ZSH generally uses category attributes to seek a semantic embedding space to transfer knowledge from seen categories to unseen ones. As a result, it may perform poorly when labeled data are insufficient. ZSH methods are mainly designed for single-modality data, which prevents their application to the widely spread multi-modal data. On the other hand, existing cross-modal hashing solutions assume that all the modalities share the same category labels, while in practice the labels of different data modalities may be different. To address these issues, we propose a general Cross-modal Zero-shot Hashing (CZHash) solution to effectively leverage unlabeled and labeled multi-modality data with different label spaces. CZHash first quantifies the composite similarity between instances using label and feature information. It then defines an objective function to achieve deep feature learning compatible with the composite similarity preserving, category attribute space learning, and hashing coding function learning. CZHash further introduces an alternative optimization procedure to jointly optimize these learning objectives. Experiments on benchmark multi-modal datasets show that CZHash significantly outperforms related representative hashing approaches both on effectiveness and adaptability.</abstract><doi>10.48550/arxiv.1908.07388</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1908.07388
ispartof
issn
language eng
recordid cdi_arxiv_primary_1908_07388
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
title Cross-modal Zero-shot Hashing
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-09T11%3A17%3A00IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Cross-modal%20Zero-shot%20Hashing&rft.au=Liu,%20Xuanwu&rft.date=2019-08-19&rft_id=info:doi/10.48550/arxiv.1908.07388&rft_dat=%3Carxiv_GOX%3E1908_07388%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true