Loading…

Partial Attention for Data-Driven Image Super Resolution Under Low Computing Cost

Low computation cost is crucial for a seamless experience on mobile consumer devices with limited resources. This study presents an efficient attention module for deep learning-based image super-resolution under low computing cost. We propose partial enhanced spatial attention (PESA) to achieve effi...

Full description

Saved in:

Bibliographic Details
Main Authors:	Nugroho, Kuntoro Adi, Windarto, Yudi Eko
Format:	Conference Proceeding
Language:	English
Subjects:	attention Attention mechanisms Computational efficiency Computational modeling Consumer electronics Convolution Costs efficient Feature extraction Interpolation partial super resolution Superresolution
Online Access:	Request full text
Tags:	Add Tag No Tags, Be the first to tag this record!

cited_by
cites
container_end_page	539
container_issue
container_start_page	538
container_title
container_volume
creator	Nugroho, Kuntoro Adi Windarto, Yudi Eko
description	Low computation cost is crucial for a seamless experience on mobile consumer devices with limited resources. This study presents an efficient attention module for deep learning-based image super-resolution under low computing cost. We propose partial enhanced spatial attention (PESA) to achieve efficient and high-performing attention modules, which draws inspiration from partial convolution for feature extraction. Utilizing an efficient super-resolution network, our approach is assessed on two super-resolution datasets and contrasted with other attention strategies. PESA obtains the lowest computing cost and model parameters, as well as the top quantitative results on both datasets.
doi_str_mv	10.1109/GCCE62371.2024.10760957
format	conference_proceeding
fullrecord	<record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_10760957</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10760957</ieee_id><sourcerecordid>10760957</sourcerecordid><originalsourceid>FETCH-ieee_primary_107609573</originalsourceid><addsrcrecordid>eNqFjsFqAjEURWNBUOr8gWB-YKYviZmYpYy2Cl3UVtcS8CmRmWRIouLfO5R27epezrmLS8iEQcEY6LePqlqWXChWcODTgoEqQUvVI5lWeiYkCClB6Rcy5KUWOczkdECyGM8AwCVwXfIh2XyZkKyp6TwldMl6R48-0IVJJl8Ee0VH1405If25tBjoN0ZfX35nO3fowKe_0co3bcfcqWsxjUj_aOqI2V--kvH7clutcouI-zbYxoT7_v-teKIft4ZCsg</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Partial Attention for Data-Driven Image Super Resolution Under Low Computing Cost</title><source>IEEE Xplore All Conference Series</source><creator>Nugroho, Kuntoro Adi ; Windarto, Yudi Eko</creator><creatorcontrib>Nugroho, Kuntoro Adi ; Windarto, Yudi Eko</creatorcontrib><description>Low computation cost is crucial for a seamless experience on mobile consumer devices with limited resources. This study presents an efficient attention module for deep learning-based image super-resolution under low computing cost. We propose partial enhanced spatial attention (PESA) to achieve efficient and high-performing attention modules, which draws inspiration from partial convolution for feature extraction. Utilizing an efficient super-resolution network, our approach is assessed on two super-resolution datasets and contrasted with other attention strategies. PESA obtains the lowest computing cost and model parameters, as well as the top quantitative results on both datasets.</description><identifier>EISSN: 2693-0854</identifier><identifier>EISBN: 9798350355079</identifier><identifier>DOI: 10.1109/GCCE62371.2024.10760957</identifier><language>eng</language><publisher>IEEE</publisher><subject>attention ; Attention mechanisms ; Computational efficiency ; Computational modeling ; Consumer electronics ; Convolution ; Costs ; efficient ; Feature extraction ; Interpolation ; partial ; super resolution ; Superresolution</subject><ispartof>IEEE Global Conference on Consumer Electronics, 2024, p.538-539</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10760957$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10760957$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Nugroho, Kuntoro Adi</creatorcontrib><creatorcontrib>Windarto, Yudi Eko</creatorcontrib><title>Partial Attention for Data-Driven Image Super Resolution Under Low Computing Cost</title><title>IEEE Global Conference on Consumer Electronics</title><addtitle>GCCE</addtitle><description>Low computation cost is crucial for a seamless experience on mobile consumer devices with limited resources. This study presents an efficient attention module for deep learning-based image super-resolution under low computing cost. We propose partial enhanced spatial attention (PESA) to achieve efficient and high-performing attention modules, which draws inspiration from partial convolution for feature extraction. Utilizing an efficient super-resolution network, our approach is assessed on two super-resolution datasets and contrasted with other attention strategies. PESA obtains the lowest computing cost and model parameters, as well as the top quantitative results on both datasets.</description><subject>attention</subject><subject>Attention mechanisms</subject><subject>Computational efficiency</subject><subject>Computational modeling</subject><subject>Consumer electronics</subject><subject>Convolution</subject><subject>Costs</subject><subject>efficient</subject><subject>Feature extraction</subject><subject>Interpolation</subject><subject>partial</subject><subject>super resolution</subject><subject>Superresolution</subject><issn>2693-0854</issn><isbn>9798350355079</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2024</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNqFjsFqAjEURWNBUOr8gWB-YKYviZmYpYy2Cl3UVtcS8CmRmWRIouLfO5R27epezrmLS8iEQcEY6LePqlqWXChWcODTgoEqQUvVI5lWeiYkCClB6Rcy5KUWOczkdECyGM8AwCVwXfIh2XyZkKyp6TwldMl6R48-0IVJJl8Ee0VH1405If25tBjoN0ZfX35nO3fowKe_0co3bcfcqWsxjUj_aOqI2V--kvH7clutcouI-zbYxoT7_v-teKIft4ZCsg</recordid><startdate>20241029</startdate><enddate>20241029</enddate><creator>Nugroho, Kuntoro Adi</creator><creator>Windarto, Yudi Eko</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>20241029</creationdate><title>Partial Attention for Data-Driven Image Super Resolution Under Low Computing Cost</title><author>Nugroho, Kuntoro Adi ; Windarto, Yudi Eko</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-ieee_primary_107609573</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2024</creationdate><topic>attention</topic><topic>Attention mechanisms</topic><topic>Computational efficiency</topic><topic>Computational modeling</topic><topic>Consumer electronics</topic><topic>Convolution</topic><topic>Costs</topic><topic>efficient</topic><topic>Feature extraction</topic><topic>Interpolation</topic><topic>partial</topic><topic>super resolution</topic><topic>Superresolution</topic><toplevel>online_resources</toplevel><creatorcontrib>Nugroho, Kuntoro Adi</creatorcontrib><creatorcontrib>Windarto, Yudi Eko</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE/IET Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Nugroho, Kuntoro Adi</au><au>Windarto, Yudi Eko</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Partial Attention for Data-Driven Image Super Resolution Under Low Computing Cost</atitle><btitle>IEEE Global Conference on Consumer Electronics</btitle><stitle>GCCE</stitle><date>2024-10-29</date><risdate>2024</risdate><spage>538</spage><epage>539</epage><pages>538-539</pages><eissn>2693-0854</eissn><eisbn>9798350355079</eisbn><abstract>Low computation cost is crucial for a seamless experience on mobile consumer devices with limited resources. This study presents an efficient attention module for deep learning-based image super-resolution under low computing cost. We propose partial enhanced spatial attention (PESA) to achieve efficient and high-performing attention modules, which draws inspiration from partial convolution for feature extraction. Utilizing an efficient super-resolution network, our approach is assessed on two super-resolution datasets and contrasted with other attention strategies. PESA obtains the lowest computing cost and model parameters, as well as the top quantitative results on both datasets.</abstract><pub>IEEE</pub><doi>10.1109/GCCE62371.2024.10760957</doi></addata></record>
fulltext	fulltext_linktorsrc
identifier	EISSN: 2693-0854
ispartof	IEEE Global Conference on Consumer Electronics, 2024, p.538-539
issn	2693-0854
language	eng
recordid	cdi_ieee_primary_10760957
source	IEEE Xplore All Conference Series
subjects	attention Attention mechanisms Computational efficiency Computational modeling Consumer electronics Convolution Costs efficient Feature extraction Interpolation partial super resolution Superresolution
title	Partial Attention for Data-Driven Image Super Resolution Under Low Computing Cost
url	http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T19%3A11%3A09IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Partial%20Attention%20for%20Data-Driven%20Image%20Super%20Resolution%20Under%20Low%20Computing%20Cost&rft.btitle=IEEE%20Global%20Conference%20on%20Consumer%20Electronics&rft.au=Nugroho,%20Kuntoro%20Adi&rft.date=2024-10-29&rft.spage=538&rft.epage=539&rft.pages=538-539&rft.eissn=2693-0854&rft_id=info:doi/10.1109/GCCE62371.2024.10760957&rft.eisbn=9798350355079&rft_dat=%3Cieee_CHZPO%3E10760957%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-ieee_primary_107609573%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=10760957&rfr_iscdi=true