Instance-weighted Central Similarity for Multi-label Image Retrieval

Deep hashing has been widely applied to large-scale image retrieval by encoding high-dimensional data points into binary codes for efficient retrieval. Compared with pairwise/triplet similarity based hash learning, central similarity based hashing can more efficiently capture the global data distrib...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Zhiwei, Peng, Hanyu
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 Zhang, Zhiwei
Peng, Hanyu
description Deep hashing has been widely applied to large-scale image retrieval by encoding high-dimensional data points into binary codes for efficient retrieval. Compared with pairwise/triplet similarity based hash learning, central similarity based hashing can more efficiently capture the global data distribution. For multi-label image retrieval, however, previous methods only use multiple hash centers with equal weights to generate one centroid as the learning target, which ignores the relationship between the weights of hash centers and the proportion of instance regions in the image. To address the above issue, we propose a two-step alternative optimization approach, Instance-weighted Central Similarity (ICS), to automatically learn the center weight corresponding to a hash code. Firstly, we apply the maximum entropy regularizer to prevent one hash center from dominating the loss function, and compute the center weights via projection gradient descent. Secondly, we update neural network parameters by standard back-propagation with fixed center weights. More importantly, the learned center weights can well reflect the proportion of foreground instances in the image. Our method achieves the state-of-the-art performance on the image retrieval benchmarks, and especially improves the mAP by 1.6%-6.4% on the MS COCO dataset.
doi_str_mv 10.48550/arxiv.2108.05274
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2108_05274</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2108_05274</sourcerecordid><originalsourceid>FETCH-LOGICAL-a674-1ee2120e53067eb24d210c94f28fcfb62701de29990daa91be3f46313e328dd13</originalsourceid><addsrcrecordid>eNotz71OwzAUhmEvHVDhApjwDTjYx86PRxQoRCpCgu7RSXxcLDkpct1C7x4oTN_26nsYu1ayME1ZyltMX-FYgJJNIUuozQW77-Z9xnkk8Ulh-57J8ZbmnDDytzCFiCnkE_e7xJ8PMQcRcaDIuwm3xF8pp0BHjJds4THu6ep_l2yzeti0T2L98ti1d2uBVW2EIgIFkkotq5oGMO7nyGiNh8aPfqiglsoRWGulQ7RqIO1NpZUmDY1zSi_ZzV_2zOg_UpgwnfpfTn_m6G9Nm0T3</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Instance-weighted Central Similarity for Multi-label Image Retrieval</title><source>arXiv.org</source><creator>Zhang, Zhiwei ; Peng, Hanyu</creator><creatorcontrib>Zhang, Zhiwei ; Peng, Hanyu</creatorcontrib><description>Deep hashing has been widely applied to large-scale image retrieval by encoding high-dimensional data points into binary codes for efficient retrieval. Compared with pairwise/triplet similarity based hash learning, central similarity based hashing can more efficiently capture the global data distribution. For multi-label image retrieval, however, previous methods only use multiple hash centers with equal weights to generate one centroid as the learning target, which ignores the relationship between the weights of hash centers and the proportion of instance regions in the image. To address the above issue, we propose a two-step alternative optimization approach, Instance-weighted Central Similarity (ICS), to automatically learn the center weight corresponding to a hash code. Firstly, we apply the maximum entropy regularizer to prevent one hash center from dominating the loss function, and compute the center weights via projection gradient descent. Secondly, we update neural network parameters by standard back-propagation with fixed center weights. More importantly, the learned center weights can well reflect the proportion of foreground instances in the image. Our method achieves the state-of-the-art performance on the image retrieval benchmarks, and especially improves the mAP by 1.6%-6.4% on the MS COCO dataset.</description><identifier>DOI: 10.48550/arxiv.2108.05274</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2021-08</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/2108.05274$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2108.05274$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Zhang, Zhiwei</creatorcontrib><creatorcontrib>Peng, Hanyu</creatorcontrib><title>Instance-weighted Central Similarity for Multi-label Image Retrieval</title><description>Deep hashing has been widely applied to large-scale image retrieval by encoding high-dimensional data points into binary codes for efficient retrieval. Compared with pairwise/triplet similarity based hash learning, central similarity based hashing can more efficiently capture the global data distribution. For multi-label image retrieval, however, previous methods only use multiple hash centers with equal weights to generate one centroid as the learning target, which ignores the relationship between the weights of hash centers and the proportion of instance regions in the image. To address the above issue, we propose a two-step alternative optimization approach, Instance-weighted Central Similarity (ICS), to automatically learn the center weight corresponding to a hash code. Firstly, we apply the maximum entropy regularizer to prevent one hash center from dominating the loss function, and compute the center weights via projection gradient descent. Secondly, we update neural network parameters by standard back-propagation with fixed center weights. More importantly, the learned center weights can well reflect the proportion of foreground instances in the image. Our method achieves the state-of-the-art performance on the image retrieval benchmarks, and especially improves the mAP by 1.6%-6.4% on the MS COCO dataset.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz71OwzAUhmEvHVDhApjwDTjYx86PRxQoRCpCgu7RSXxcLDkpct1C7x4oTN_26nsYu1ayME1ZyltMX-FYgJJNIUuozQW77-Z9xnkk8Ulh-57J8ZbmnDDytzCFiCnkE_e7xJ8PMQcRcaDIuwm3xF8pp0BHjJds4THu6ep_l2yzeti0T2L98ti1d2uBVW2EIgIFkkotq5oGMO7nyGiNh8aPfqiglsoRWGulQ7RqIO1NpZUmDY1zSi_ZzV_2zOg_UpgwnfpfTn_m6G9Nm0T3</recordid><startdate>20210811</startdate><enddate>20210811</enddate><creator>Zhang, Zhiwei</creator><creator>Peng, Hanyu</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20210811</creationdate><title>Instance-weighted Central Similarity for Multi-label Image Retrieval</title><author>Zhang, Zhiwei ; Peng, Hanyu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a674-1ee2120e53067eb24d210c94f28fcfb62701de29990daa91be3f46313e328dd13</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Zhiwei</creatorcontrib><creatorcontrib>Peng, Hanyu</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Zhang, Zhiwei</au><au>Peng, Hanyu</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Instance-weighted Central Similarity for Multi-label Image Retrieval</atitle><date>2021-08-11</date><risdate>2021</risdate><abstract>Deep hashing has been widely applied to large-scale image retrieval by encoding high-dimensional data points into binary codes for efficient retrieval. Compared with pairwise/triplet similarity based hash learning, central similarity based hashing can more efficiently capture the global data distribution. For multi-label image retrieval, however, previous methods only use multiple hash centers with equal weights to generate one centroid as the learning target, which ignores the relationship between the weights of hash centers and the proportion of instance regions in the image. To address the above issue, we propose a two-step alternative optimization approach, Instance-weighted Central Similarity (ICS), to automatically learn the center weight corresponding to a hash code. Firstly, we apply the maximum entropy regularizer to prevent one hash center from dominating the loss function, and compute the center weights via projection gradient descent. Secondly, we update neural network parameters by standard back-propagation with fixed center weights. More importantly, the learned center weights can well reflect the proportion of foreground instances in the image. Our method achieves the state-of-the-art performance on the image retrieval benchmarks, and especially improves the mAP by 1.6%-6.4% on the MS COCO dataset.</abstract><doi>10.48550/arxiv.2108.05274</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2108.05274
ispartof
issn
language eng
recordid cdi_arxiv_primary_2108_05274
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title Instance-weighted Central Similarity for Multi-label Image Retrieval
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T04%3A38%3A25IST&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=Instance-weighted%20Central%20Similarity%20for%20Multi-label%20Image%20Retrieval&rft.au=Zhang,%20Zhiwei&rft.date=2021-08-11&rft_id=info:doi/10.48550/arxiv.2108.05274&rft_dat=%3Carxiv_GOX%3E2108_05274%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