Visual Confusion Label Tree For Image Classification
Convolution neural network models are widely used in image classification tasks. However, the running time of such models is so long that it is not the conforming to the strict real-time requirement of mobile devices. In order to optimize models and meet the requirement mentioned above, we propose a...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2019-06 |
---|---|
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 | Liu, Yuntao Dou, Yong Jin, Ruochun Li, Rongchun |
description | Convolution neural network models are widely used in image classification tasks. However, the running time of such models is so long that it is not the conforming to the strict real-time requirement of mobile devices. In order to optimize models and meet the requirement mentioned above, we propose a method that replaces the fully-connected layers of convolution neural network models with a tree classifier. Specifically, we construct a Visual Confusion Label Tree based on the output of the convolution neural network models, and use a multi-kernel SVM plus classifier with hierarchical constraints to train the tree classifier. Focusing on those confusion subsets instead of the entire set of categories makes the tree classifier more discriminative and the replacement of the fully-connected layers reduces the original running time. Experiments show that our tree classifier obtains a significant improvement over the state-of-the-art tree classifier by 4.3% and 2.4% in terms of top-1 accuracy on CIFAR-100 and ImageNet datasets respectively. Additionally, our method achieves 124x and 115x speedup ratio compared with fully-connected layers on AlexNet and VGG16 without accuracy decline. |
doi_str_mv | 10.48550/arxiv.1906.02012 |
format | Article |
fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_1906_02012</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2235949443</sourcerecordid><originalsourceid>FETCH-LOGICAL-a523-486c1a515b8b98352dfd6b4e521083ec1a83893192ab3cfb10a41d64762e5ec43</originalsourceid><addsrcrecordid>eNotj1FLwzAUhYMgOOZ-gE8GfG5N7k2y9FGK00HBl-JruWlTyejWmayi_966-XQezsfhfIzdSZErq7V4pPgdvnJZCJMLEBKu2AIQZWYVwA1bpbQTQoBZg9a4YOo9pIkGXo6HfkphPPCKnB94Hb3nmzHy7Z4-PC8HSin0oaXTzNyy656G5Ff_uWT15rkuX7Pq7WVbPlUZacBMWdNK0lI76wqLGrq-M055DVJY9HNn0RYoCyCHbe-kICU7o9YGvPatwiW7v8yelZpjDHuKP82fWnNWm4mHC3GM4-fk06nZjVM8zJ8aANSFKpRC_AWcb08t</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2235949443</pqid></control><display><type>article</type><title>Visual Confusion Label Tree For Image Classification</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Liu, Yuntao ; Dou, Yong ; Jin, Ruochun ; Li, Rongchun</creator><creatorcontrib>Liu, Yuntao ; Dou, Yong ; Jin, Ruochun ; Li, Rongchun</creatorcontrib><description>Convolution neural network models are widely used in image classification tasks. However, the running time of such models is so long that it is not the conforming to the strict real-time requirement of mobile devices. In order to optimize models and meet the requirement mentioned above, we propose a method that replaces the fully-connected layers of convolution neural network models with a tree classifier. Specifically, we construct a Visual Confusion Label Tree based on the output of the convolution neural network models, and use a multi-kernel SVM plus classifier with hierarchical constraints to train the tree classifier. Focusing on those confusion subsets instead of the entire set of categories makes the tree classifier more discriminative and the replacement of the fully-connected layers reduces the original running time. Experiments show that our tree classifier obtains a significant improvement over the state-of-the-art tree classifier by 4.3% and 2.4% in terms of top-1 accuracy on CIFAR-100 and ImageNet datasets respectively. Additionally, our method achieves 124x and 115x speedup ratio compared with fully-connected layers on AlexNet and VGG16 without accuracy decline.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.1906.02012</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial neural networks ; Classifiers ; Computer Science - Computer Vision and Pattern Recognition ; Confusion ; Convolution ; Electronic devices ; Image classification ; Neural networks</subject><ispartof>arXiv.org, 2019-06</ispartof><rights>2019. 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><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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,780,881,27904</link.rule.ids><backlink>$$Uhttps://doi.org/10.1109/ICME.2018.8486612$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.48550/arXiv.1906.02012$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Liu, Yuntao</creatorcontrib><creatorcontrib>Dou, Yong</creatorcontrib><creatorcontrib>Jin, Ruochun</creatorcontrib><creatorcontrib>Li, Rongchun</creatorcontrib><title>Visual Confusion Label Tree For Image Classification</title><title>arXiv.org</title><description>Convolution neural network models are widely used in image classification tasks. However, the running time of such models is so long that it is not the conforming to the strict real-time requirement of mobile devices. In order to optimize models and meet the requirement mentioned above, we propose a method that replaces the fully-connected layers of convolution neural network models with a tree classifier. Specifically, we construct a Visual Confusion Label Tree based on the output of the convolution neural network models, and use a multi-kernel SVM plus classifier with hierarchical constraints to train the tree classifier. Focusing on those confusion subsets instead of the entire set of categories makes the tree classifier more discriminative and the replacement of the fully-connected layers reduces the original running time. Experiments show that our tree classifier obtains a significant improvement over the state-of-the-art tree classifier by 4.3% and 2.4% in terms of top-1 accuracy on CIFAR-100 and ImageNet datasets respectively. Additionally, our method achieves 124x and 115x speedup ratio compared with fully-connected layers on AlexNet and VGG16 without accuracy decline.</description><subject>Artificial neural networks</subject><subject>Classifiers</subject><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Confusion</subject><subject>Convolution</subject><subject>Electronic devices</subject><subject>Image classification</subject><subject>Neural networks</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><sourceid>GOX</sourceid><recordid>eNotj1FLwzAUhYMgOOZ-gE8GfG5N7k2y9FGK00HBl-JruWlTyejWmayi_966-XQezsfhfIzdSZErq7V4pPgdvnJZCJMLEBKu2AIQZWYVwA1bpbQTQoBZg9a4YOo9pIkGXo6HfkphPPCKnB94Hb3nmzHy7Z4-PC8HSin0oaXTzNyy656G5Ff_uWT15rkuX7Pq7WVbPlUZacBMWdNK0lI76wqLGrq-M055DVJY9HNn0RYoCyCHbe-kICU7o9YGvPatwiW7v8yelZpjDHuKP82fWnNWm4mHC3GM4-fk06nZjVM8zJ8aANSFKpRC_AWcb08t</recordid><startdate>20190605</startdate><enddate>20190605</enddate><creator>Liu, Yuntao</creator><creator>Dou, Yong</creator><creator>Jin, Ruochun</creator><creator>Li, Rongchun</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><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20190605</creationdate><title>Visual Confusion Label Tree For Image Classification</title><author>Liu, Yuntao ; Dou, Yong ; Jin, Ruochun ; Li, Rongchun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a523-486c1a515b8b98352dfd6b4e521083ec1a83893192ab3cfb10a41d64762e5ec43</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Artificial neural networks</topic><topic>Classifiers</topic><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Confusion</topic><topic>Convolution</topic><topic>Electronic devices</topic><topic>Image classification</topic><topic>Neural networks</topic><toplevel>online_resources</toplevel><creatorcontrib>Liu, Yuntao</creatorcontrib><creatorcontrib>Dou, Yong</creatorcontrib><creatorcontrib>Jin, Ruochun</creatorcontrib><creatorcontrib>Li, Rongchun</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><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Liu, Yuntao</au><au>Dou, Yong</au><au>Jin, Ruochun</au><au>Li, Rongchun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Visual Confusion Label Tree For Image Classification</atitle><jtitle>arXiv.org</jtitle><date>2019-06-05</date><risdate>2019</risdate><eissn>2331-8422</eissn><abstract>Convolution neural network models are widely used in image classification tasks. However, the running time of such models is so long that it is not the conforming to the strict real-time requirement of mobile devices. In order to optimize models and meet the requirement mentioned above, we propose a method that replaces the fully-connected layers of convolution neural network models with a tree classifier. Specifically, we construct a Visual Confusion Label Tree based on the output of the convolution neural network models, and use a multi-kernel SVM plus classifier with hierarchical constraints to train the tree classifier. Focusing on those confusion subsets instead of the entire set of categories makes the tree classifier more discriminative and the replacement of the fully-connected layers reduces the original running time. Experiments show that our tree classifier obtains a significant improvement over the state-of-the-art tree classifier by 4.3% and 2.4% in terms of top-1 accuracy on CIFAR-100 and ImageNet datasets respectively. Additionally, our method achieves 124x and 115x speedup ratio compared with fully-connected layers on AlexNet and VGG16 without accuracy decline.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.1906.02012</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2019-06 |
issn | 2331-8422 |
language | eng |
recordid | cdi_arxiv_primary_1906_02012 |
source | arXiv.org; Free E- Journals |
subjects | Artificial neural networks Classifiers Computer Science - Computer Vision and Pattern Recognition Confusion Convolution Electronic devices Image classification Neural networks |
title | Visual Confusion Label Tree For Image Classification |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T23%3A39%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Visual%20Confusion%20Label%20Tree%20For%20Image%20Classification&rft.jtitle=arXiv.org&rft.au=Liu,%20Yuntao&rft.date=2019-06-05&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.1906.02012&rft_dat=%3Cproquest_arxiv%3E2235949443%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2235949443&rft_id=info:pmid/&rfr_iscdi=true |