Loading…

Influence of Different Activation Functions on Deep Learning Models in Indoor Scene Images Classification

The success of deep learning in the field of computer vision and object recognition has made significant breakthroughs, especially in improving recognition accuracy. The scene recognition algorithms have been evolved over the years because of the developments in machine learning and deep convolution...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition and image analysis 2022-03, Vol.32 (1), p.78-88
Main Authors: Anami, Basavaraj S., Sagarnal, Chetan V.
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c316t-88c198739c624a2e8cf59640efef407dbee130ea35b54162abc46283a52657e73
cites cdi_FETCH-LOGICAL-c316t-88c198739c624a2e8cf59640efef407dbee130ea35b54162abc46283a52657e73
container_end_page 88
container_issue 1
container_start_page 78
container_title Pattern recognition and image analysis
container_volume 32
creator Anami, Basavaraj S.
Sagarnal, Chetan V.
description The success of deep learning in the field of computer vision and object recognition has made significant breakthroughs, especially in improving recognition accuracy. The scene recognition algorithms have been evolved over the years because of the developments in machine learning and deep convolution neural networks (DCNNs). In this paper, the classification of indoor scenes using three deep learning models, namely, ResNet, MobileNet, and EfficientNet is attempted. The influence of activation functions on classification accuracy is being explored. Three activation functions, namely, tanh, ReLU, and sigmoid, are deployed in the work. The MIT-67 indoor dataset is split into scenes with and without people to test its effect on the accuracy of classification. The novelty of the work includes splitting the dataset, based on the spatial layout and segregating, into two groups, namely, with people and without people. Amongst the three pre-trained models, EfficientNet has given good results.
doi_str_mv 10.1134/S1054661821040039
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2640580683</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2640580683</sourcerecordid><originalsourceid>FETCH-LOGICAL-c316t-88c198739c624a2e8cf59640efef407dbee130ea35b54162abc46283a52657e73</originalsourceid><addsrcrecordid>eNp1kEtLAzEUhYMoWKs_wF3A9Wjek1mW1keh4qK6HtL0pqRMk5rMCP57Uyu4EFf3XM4534WL0DUlt5RycbekRAqlqGaUCEJ4c4JGVEpZKUbZadHFrg7-ObrIeUsI0bRhI-TnwXUDBAs4OjzzzkGC0OOJ7f2H6X0M-GEI9iAyLssMYI8XYFLwYYOf4xq6jH3A87COMeGlhQB4vjMbyHjamZy98_abc4nOnOkyXP3MMXp7uH-dPlWLl8f5dLKoLKeqr7S2tNE1b6xiwjDQ1slGCQIOnCD1egVAOQHD5UoKqphZWaGY5kYyJWuo-RjdHLn7FN8HyH27jUMK5WTLCkdqojQvKXpM2RRzTuDaffI7kz5bStrDR9s_Hy0dduzkkg0bSL_k_0tfL6x3TQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2640580683</pqid></control><display><type>article</type><title>Influence of Different Activation Functions on Deep Learning Models in Indoor Scene Images Classification</title><source>Springer Link</source><creator>Anami, Basavaraj S. ; Sagarnal, Chetan V.</creator><creatorcontrib>Anami, Basavaraj S. ; Sagarnal, Chetan V.</creatorcontrib><description>The success of deep learning in the field of computer vision and object recognition has made significant breakthroughs, especially in improving recognition accuracy. The scene recognition algorithms have been evolved over the years because of the developments in machine learning and deep convolution neural networks (DCNNs). In this paper, the classification of indoor scenes using three deep learning models, namely, ResNet, MobileNet, and EfficientNet is attempted. The influence of activation functions on classification accuracy is being explored. Three activation functions, namely, tanh, ReLU, and sigmoid, are deployed in the work. The MIT-67 indoor dataset is split into scenes with and without people to test its effect on the accuracy of classification. The novelty of the work includes splitting the dataset, based on the spatial layout and segregating, into two groups, namely, with people and without people. Amongst the three pre-trained models, EfficientNet has given good results.</description><identifier>ISSN: 1054-6618</identifier><identifier>EISSN: 1555-6212</identifier><identifier>DOI: 10.1134/S1054661821040039</identifier><language>eng</language><publisher>Moscow: Pleiades Publishing</publisher><subject>Accuracy ; Algorithms ; Application Problems ; Artificial neural networks ; Classification ; Computer Science ; Computer vision ; Datasets ; Deep learning ; Image classification ; Image Processing and Computer Vision ; Machine learning ; Object recognition ; Pattern Recognition</subject><ispartof>Pattern recognition and image analysis, 2022-03, Vol.32 (1), p.78-88</ispartof><rights>Pleiades Publishing, Ltd. 2022. ISSN 1054-6618, Pattern Recognition and Image Analysis, 2022, Vol. 32, No. 1, pp. 78–88. © Pleiades Publishing, Ltd., 2022.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c316t-88c198739c624a2e8cf59640efef407dbee130ea35b54162abc46283a52657e73</citedby><cites>FETCH-LOGICAL-c316t-88c198739c624a2e8cf59640efef407dbee130ea35b54162abc46283a52657e73</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Anami, Basavaraj S.</creatorcontrib><creatorcontrib>Sagarnal, Chetan V.</creatorcontrib><title>Influence of Different Activation Functions on Deep Learning Models in Indoor Scene Images Classification</title><title>Pattern recognition and image analysis</title><addtitle>Pattern Recognit. Image Anal</addtitle><description>The success of deep learning in the field of computer vision and object recognition has made significant breakthroughs, especially in improving recognition accuracy. The scene recognition algorithms have been evolved over the years because of the developments in machine learning and deep convolution neural networks (DCNNs). In this paper, the classification of indoor scenes using three deep learning models, namely, ResNet, MobileNet, and EfficientNet is attempted. The influence of activation functions on classification accuracy is being explored. Three activation functions, namely, tanh, ReLU, and sigmoid, are deployed in the work. The MIT-67 indoor dataset is split into scenes with and without people to test its effect on the accuracy of classification. The novelty of the work includes splitting the dataset, based on the spatial layout and segregating, into two groups, namely, with people and without people. Amongst the three pre-trained models, EfficientNet has given good results.</description><subject>Accuracy</subject><subject>Algorithms</subject><subject>Application Problems</subject><subject>Artificial neural networks</subject><subject>Classification</subject><subject>Computer Science</subject><subject>Computer vision</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>Image classification</subject><subject>Image Processing and Computer Vision</subject><subject>Machine learning</subject><subject>Object recognition</subject><subject>Pattern Recognition</subject><issn>1054-6618</issn><issn>1555-6212</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNp1kEtLAzEUhYMoWKs_wF3A9Wjek1mW1keh4qK6HtL0pqRMk5rMCP57Uyu4EFf3XM4534WL0DUlt5RycbekRAqlqGaUCEJ4c4JGVEpZKUbZadHFrg7-ObrIeUsI0bRhI-TnwXUDBAs4OjzzzkGC0OOJ7f2H6X0M-GEI9iAyLssMYI8XYFLwYYOf4xq6jH3A87COMeGlhQB4vjMbyHjamZy98_abc4nOnOkyXP3MMXp7uH-dPlWLl8f5dLKoLKeqr7S2tNE1b6xiwjDQ1slGCQIOnCD1egVAOQHD5UoKqphZWaGY5kYyJWuo-RjdHLn7FN8HyH27jUMK5WTLCkdqojQvKXpM2RRzTuDaffI7kz5bStrDR9s_Hy0dduzkkg0bSL_k_0tfL6x3TQ</recordid><startdate>20220301</startdate><enddate>20220301</enddate><creator>Anami, Basavaraj S.</creator><creator>Sagarnal, Chetan V.</creator><general>Pleiades Publishing</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20220301</creationdate><title>Influence of Different Activation Functions on Deep Learning Models in Indoor Scene Images Classification</title><author>Anami, Basavaraj S. ; Sagarnal, Chetan V.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c316t-88c198739c624a2e8cf59640efef407dbee130ea35b54162abc46283a52657e73</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Accuracy</topic><topic>Algorithms</topic><topic>Application Problems</topic><topic>Artificial neural networks</topic><topic>Classification</topic><topic>Computer Science</topic><topic>Computer vision</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>Image classification</topic><topic>Image Processing and Computer Vision</topic><topic>Machine learning</topic><topic>Object recognition</topic><topic>Pattern Recognition</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Anami, Basavaraj S.</creatorcontrib><creatorcontrib>Sagarnal, Chetan V.</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Pattern recognition and image analysis</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Anami, Basavaraj S.</au><au>Sagarnal, Chetan V.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Influence of Different Activation Functions on Deep Learning Models in Indoor Scene Images Classification</atitle><jtitle>Pattern recognition and image analysis</jtitle><stitle>Pattern Recognit. Image Anal</stitle><date>2022-03-01</date><risdate>2022</risdate><volume>32</volume><issue>1</issue><spage>78</spage><epage>88</epage><pages>78-88</pages><issn>1054-6618</issn><eissn>1555-6212</eissn><abstract>The success of deep learning in the field of computer vision and object recognition has made significant breakthroughs, especially in improving recognition accuracy. The scene recognition algorithms have been evolved over the years because of the developments in machine learning and deep convolution neural networks (DCNNs). In this paper, the classification of indoor scenes using three deep learning models, namely, ResNet, MobileNet, and EfficientNet is attempted. The influence of activation functions on classification accuracy is being explored. Three activation functions, namely, tanh, ReLU, and sigmoid, are deployed in the work. The MIT-67 indoor dataset is split into scenes with and without people to test its effect on the accuracy of classification. The novelty of the work includes splitting the dataset, based on the spatial layout and segregating, into two groups, namely, with people and without people. Amongst the three pre-trained models, EfficientNet has given good results.</abstract><cop>Moscow</cop><pub>Pleiades Publishing</pub><doi>10.1134/S1054661821040039</doi><tpages>11</tpages></addata></record>
fulltext fulltext
identifier ISSN: 1054-6618
ispartof Pattern recognition and image analysis, 2022-03, Vol.32 (1), p.78-88
issn 1054-6618
1555-6212
language eng
recordid cdi_proquest_journals_2640580683
source Springer Link
subjects Accuracy
Algorithms
Application Problems
Artificial neural networks
Classification
Computer Science
Computer vision
Datasets
Deep learning
Image classification
Image Processing and Computer Vision
Machine learning
Object recognition
Pattern Recognition
title Influence of Different Activation Functions on Deep Learning Models in Indoor Scene Images Classification
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T14%3A19%3A26IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Influence%20of%20Different%20Activation%20Functions%20on%20Deep%20Learning%20Models%20in%20Indoor%20Scene%20Images%20Classification&rft.jtitle=Pattern%20recognition%20and%20image%20analysis&rft.au=Anami,%20Basavaraj%20S.&rft.date=2022-03-01&rft.volume=32&rft.issue=1&rft.spage=78&rft.epage=88&rft.pages=78-88&rft.issn=1054-6618&rft.eissn=1555-6212&rft_id=info:doi/10.1134/S1054661821040039&rft_dat=%3Cproquest_cross%3E2640580683%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c316t-88c198739c624a2e8cf59640efef407dbee130ea35b54162abc46283a52657e73%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2640580683&rft_id=info:pmid/&rfr_iscdi=true