Investigating the Impact of Randomness on Reproducibility in Computer Vision: A Study on Applications in Civil Engineering and Medicine

Reproducibility is essential for scientific research. However, in computer vision, achieving consistent results is challenging due to various factors. One influential, yet often unrecognized, factor is CUDA-induced randomness. Despite CUDA's advantages for accelerating algorithm execution on GP...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-09
Main Authors: Eryılmaz, Bahadır, Koraş, Osman Alperen, Schlötterer, Jörg, Seifert, Christin
Format: Article
Language:English
Subjects:
Algorithms
Computer vision
Datasets
Randomness
Reproducibility
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Eryılmaz, Bahadır
Koraş, Osman Alperen
Schlötterer, Jörg
Seifert, Christin
description Reproducibility is essential for scientific research. However, in computer vision, achieving consistent results is challenging due to various factors. One influential, yet often unrecognized, factor is CUDA-induced randomness. Despite CUDA's advantages for accelerating algorithm execution on GPUs, if not controlled, its behavior across multiple executions remains non-deterministic. While reproducibility issues in ML being researched, the implications of CUDA-induced randomness in application are yet to be understood. Our investigation focuses on this randomness across one standard benchmark dataset and two real-world datasets in an isolated environment. Our results show that CUDA-induced randomness can account for differences up to 4.77% in performance scores. We find that managing this variability for reproducibility may entail increased runtime or reduce performance, but that disadvantages are not as significant as reported in previous studies.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3113849418</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3113849418</sourcerecordid><originalsourceid>FETCH-proquest_journals_31138494183</originalsourceid><addsrcrecordid>eNqNjsHKwjAQhIMgKOo7LHgW2qRq9Sbiz-_Bi4pXqe1aV9pNbBLBJ_C1jeIDeBqY-ZiZluhKpeJRmkjZEQNrr1EUyclUjseqK55rvqN1VGaOuAR3QVjXJssd6DNsMy50zWgtaIYtmkYXPqcTVeQeQAxLXRvvsIEDWdI8hwXsnC8eb3xhTEV5qNVsPyzdqYIVl8SIzXsstMMGC8qD0xftc1ZZHHy1J4Z_q_3yfxQ2bz48PF61bzhERxXHKk1mSZyq36gXjVdTIQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3113849418</pqid></control><display><type>article</type><title>Investigating the Impact of Randomness on Reproducibility in Computer Vision: A Study on Applications in Civil Engineering and Medicine</title><source>Publicly Available Content Database</source><creator>Eryılmaz, Bahadır ; Koraş, Osman Alperen ; Schlötterer, Jörg ; Seifert, Christin</creator><creatorcontrib>Eryılmaz, Bahadır ; Koraş, Osman Alperen ; Schlötterer, Jörg ; Seifert, Christin</creatorcontrib><description>Reproducibility is essential for scientific research. However, in computer vision, achieving consistent results is challenging due to various factors. One influential, yet often unrecognized, factor is CUDA-induced randomness. Despite CUDA's advantages for accelerating algorithm execution on GPUs, if not controlled, its behavior across multiple executions remains non-deterministic. While reproducibility issues in ML being researched, the implications of CUDA-induced randomness in application are yet to be understood. Our investigation focuses on this randomness across one standard benchmark dataset and two real-world datasets in an isolated environment. Our results show that CUDA-induced randomness can account for differences up to 4.77% in performance scores. We find that managing this variability for reproducibility may entail increased runtime or reduce performance, but that disadvantages are not as significant as reported in previous studies.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Computer vision ; Datasets ; Randomness ; Reproducibility</subject><ispartof>arXiv.org, 2024-09</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (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>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/3113849418?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25752,37011,44589</link.rule.ids></links><search><creatorcontrib>Eryılmaz, Bahadır</creatorcontrib><creatorcontrib>Koraş, Osman Alperen</creatorcontrib><creatorcontrib>Schlötterer, Jörg</creatorcontrib><creatorcontrib>Seifert, Christin</creatorcontrib><title>Investigating the Impact of Randomness on Reproducibility in Computer Vision: A Study on Applications in Civil Engineering and Medicine</title><title>arXiv.org</title><description>Reproducibility is essential for scientific research. However, in computer vision, achieving consistent results is challenging due to various factors. One influential, yet often unrecognized, factor is CUDA-induced randomness. Despite CUDA's advantages for accelerating algorithm execution on GPUs, if not controlled, its behavior across multiple executions remains non-deterministic. While reproducibility issues in ML being researched, the implications of CUDA-induced randomness in application are yet to be understood. Our investigation focuses on this randomness across one standard benchmark dataset and two real-world datasets in an isolated environment. Our results show that CUDA-induced randomness can account for differences up to 4.77% in performance scores. We find that managing this variability for reproducibility may entail increased runtime or reduce performance, but that disadvantages are not as significant as reported in previous studies.</description><subject>Algorithms</subject><subject>Computer vision</subject><subject>Datasets</subject><subject>Randomness</subject><subject>Reproducibility</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNjsHKwjAQhIMgKOo7LHgW2qRq9Sbiz-_Bi4pXqe1aV9pNbBLBJ_C1jeIDeBqY-ZiZluhKpeJRmkjZEQNrr1EUyclUjseqK55rvqN1VGaOuAR3QVjXJssd6DNsMy50zWgtaIYtmkYXPqcTVeQeQAxLXRvvsIEDWdI8hwXsnC8eb3xhTEV5qNVsPyzdqYIVl8SIzXsstMMGC8qD0xftc1ZZHHy1J4Z_q_3yfxQ2bz48PF61bzhERxXHKk1mSZyq36gXjVdTIQ</recordid><startdate>20240919</startdate><enddate>20240919</enddate><creator>Eryılmaz, Bahadır</creator><creator>Koraş, Osman Alperen</creator><creator>Schlötterer, Jörg</creator><creator>Seifert, Christin</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>20240919</creationdate><title>Investigating the Impact of Randomness on Reproducibility in Computer Vision: A Study on Applications in Civil Engineering and Medicine</title><author>Eryılmaz, Bahadır ; Koraş, Osman Alperen ; Schlötterer, Jörg ; Seifert, Christin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_31138494183</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Algorithms</topic><topic>Computer vision</topic><topic>Datasets</topic><topic>Randomness</topic><topic>Reproducibility</topic><toplevel>online_resources</toplevel><creatorcontrib>Eryılmaz, Bahadır</creatorcontrib><creatorcontrib>Koraş, Osman Alperen</creatorcontrib><creatorcontrib>Schlötterer, Jörg</creatorcontrib><creatorcontrib>Seifert, Christin</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</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>Eryılmaz, Bahadır</au><au>Koraş, Osman Alperen</au><au>Schlötterer, Jörg</au><au>Seifert, Christin</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Investigating the Impact of Randomness on Reproducibility in Computer Vision: A Study on Applications in Civil Engineering and Medicine</atitle><jtitle>arXiv.org</jtitle><date>2024-09-19</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Reproducibility is essential for scientific research. However, in computer vision, achieving consistent results is challenging due to various factors. One influential, yet often unrecognized, factor is CUDA-induced randomness. Despite CUDA's advantages for accelerating algorithm execution on GPUs, if not controlled, its behavior across multiple executions remains non-deterministic. While reproducibility issues in ML being researched, the implications of CUDA-induced randomness in application are yet to be understood. Our investigation focuses on this randomness across one standard benchmark dataset and two real-world datasets in an isolated environment. Our results show that CUDA-induced randomness can account for differences up to 4.77% in performance scores. We find that managing this variability for reproducibility may entail increased runtime or reduce performance, but that disadvantages are not as significant as reported in previous studies.</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, 2024-09
issn 2331-8422
language eng
recordid cdi_proquest_journals_3113849418
source Publicly Available Content Database
subjects Algorithms
Computer vision
Datasets
Randomness
Reproducibility
title Investigating the Impact of Randomness on Reproducibility in Computer Vision: A Study on Applications in Civil Engineering and Medicine
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T04%3A16%3A58IST&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=Investigating%20the%20Impact%20of%20Randomness%20on%20Reproducibility%20in%20Computer%20Vision:%20A%20Study%20on%20Applications%20in%20Civil%20Engineering%20and%20Medicine&rft.jtitle=arXiv.org&rft.au=Ery%C4%B1lmaz,%20Bahad%C4%B1r&rft.date=2024-09-19&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3113849418%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_31138494183%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3113849418&rft_id=info:pmid/&rfr_iscdi=true