{"id":"https://openalex.org/W4387415278","doi":"https://doi.org/10.1109/tai.2023.3322394","title":"Minimizing Parameter Overhead in Self-Supervised Models for Target Task","display_name":"Minimizing Parameter Overhead in Self-Supervised Models for Target Task","publication_year":2023,"publication_date":"2023-10-06","ids":{"openalex":"https://openalex.org/W4387415278","doi":"https://doi.org/10.1109/tai.2023.3322394"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2023.3322394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2023.3322394","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043069606","display_name":"Jaydeep Kishore","orcid":"https://orcid.org/0000-0003-1839-5082"},"institutions":[{"id":"https://openalex.org/I26604189","display_name":"Shiv Nadar University","ror":"https://ror.org/05aqahr97","country_code":"IN","type":"education","lineage":["https://openalex.org/I26604189"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Jaydeep Kishore","raw_affiliation_strings":["Department of Design, Shiv Nadar University, Noida, India","Computer Science and Engineering, Shiv Nadar University - Campus Delhi NCR, Uttar Pradesh, India"],"affiliations":[{"raw_affiliation_string":"Department of Design, Shiv Nadar University, Noida, India","institution_ids":["https://openalex.org/I26604189"]},{"raw_affiliation_string":"Computer Science and Engineering, Shiv Nadar University - Campus Delhi NCR, Uttar Pradesh, India","institution_ids":["https://openalex.org/I26604189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070435685","display_name":"Snehasis Mukherjee","orcid":"https://orcid.org/0000-0002-2196-8980"},"institutions":[{"id":"https://openalex.org/I26604189","display_name":"Shiv Nadar University","ror":"https://ror.org/05aqahr97","country_code":"IN","type":"education","lineage":["https://openalex.org/I26604189"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Snehasis Mukherjee","raw_affiliation_strings":["Department of Design, Shiv Nadar University, Noida, India","Computer Science and Engineering, Shiv Nadar University - Campus Delhi NCR, Uttar Pradesh, India"],"affiliations":[{"raw_affiliation_string":"Department of Design, Shiv Nadar University, Noida, India","institution_ids":["https://openalex.org/I26604189"]},{"raw_affiliation_string":"Computer Science and Engineering, Shiv Nadar University - Campus Delhi NCR, Uttar Pradesh, India","institution_ids":["https://openalex.org/I26604189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043069606"],"corresponding_institution_ids":["https://openalex.org/I26604189"],"apc_list":null,"apc_paid":null,"fwci":0.6983,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75983762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"5","issue":"4","first_page":"1635","last_page":"1646"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8279550671577454},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.7184919714927673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.715569019317627},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6980752348899841},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5537247061729431},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4706254005432129},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4646655321121216},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4582144618034363},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.44883251190185547},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41724249720573425},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.4127807021141052},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2377314567565918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8279550671577454},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.7184919714927673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.715569019317627},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6980752348899841},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5537247061729431},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4706254005432129},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4646655321121216},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4582144618034363},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.44883251190185547},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41724249720573425},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.4127807021141052},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2377314567565918},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2023.3322394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2023.3322394","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W1977295328","https://openalex.org/W2108598243","https://openalex.org/W2155904486","https://openalex.org/W2194775991","https://openalex.org/W2321533354","https://openalex.org/W2326925005","https://openalex.org/W2533598788","https://openalex.org/W2621097878","https://openalex.org/W2738900641","https://openalex.org/W2913657597","https://openalex.org/W2928842276","https://openalex.org/W2946547492","https://openalex.org/W2963420272","https://openalex.org/W2963821229","https://openalex.org/W2966160658","https://openalex.org/W2967733054","https://openalex.org/W2989221291","https://openalex.org/W2997209505","https://openalex.org/W3003242248","https://openalex.org/W3013072869","https://openalex.org/W3021633728","https://openalex.org/W3035524453","https://openalex.org/W3035725276","https://openalex.org/W3045004532","https://openalex.org/W3082701951","https://openalex.org/W3089661409","https://openalex.org/W3112889778","https://openalex.org/W3118608800","https://openalex.org/W3120818306","https://openalex.org/W3130635520","https://openalex.org/W3135939397","https://openalex.org/W3145450063","https://openalex.org/W3168997536","https://openalex.org/W3171007011","https://openalex.org/W3192682950","https://openalex.org/W3210441640","https://openalex.org/W3217656104","https://openalex.org/W4200061105","https://openalex.org/W4214642259","https://openalex.org/W4289761856","https://openalex.org/W4293070598","https://openalex.org/W4293879871","https://openalex.org/W4312695107","https://openalex.org/W4312745848","https://openalex.org/W4312805352","https://openalex.org/W4313055538","https://openalex.org/W4313125078","https://openalex.org/W4320481801","https://openalex.org/W4391175312","https://openalex.org/W6676179485","https://openalex.org/W6677088747","https://openalex.org/W6729956949","https://openalex.org/W6741969688","https://openalex.org/W6752515464","https://openalex.org/W6753146606","https://openalex.org/W6762573206","https://openalex.org/W6763416564","https://openalex.org/W6771915822","https://openalex.org/W6779977557","https://openalex.org/W6779997284","https://openalex.org/W6780730929","https://openalex.org/W6782806660","https://openalex.org/W6787972765","https://openalex.org/W6803945485","https://openalex.org/W7015890786"],"related_works":["https://openalex.org/W4233965824","https://openalex.org/W2607442583","https://openalex.org/W3199199693","https://openalex.org/W4286970057","https://openalex.org/W2967237190","https://openalex.org/W3028852288","https://openalex.org/W4323366554","https://openalex.org/W2405673391","https://openalex.org/W4292388060","https://openalex.org/W2200000192"],"abstract_inverted_index":{"Supervised":[0],"deep":[1],"learning":[2,81],"models":[3,30,42],"encounter":[4],"two":[5,70],"significant":[6],"challenges:":[7],"the":[8,14,39,44,51,69,73,92,105,125,129,149,153,157,174,178,188,200,209,213,219,229,241,288],"labeled":[9,47,196],"datasets":[10,255],"for":[11,46,83,152,184],"training":[12,48],"and":[13,23,56,131,221,239,264,272,276,293],"parameter":[15,54],"overhead,":[16],"which":[17,89],"leads":[18],"to":[19,67,212],"extensive":[20],"GPU":[21,57],"usage":[22,58],"other":[24],"computational":[25],"resource":[26],"requirements.":[27],"Several":[28],"CNN":[29,116,130],"show":[31],"state-of-the-art":[32],"performance":[33],"while":[34],"compromising":[35,156],"with":[36,164,224,246,256,279,290],"either":[37],"of":[38,53,72,127,250,260,282],"challenges.":[40,166],"Self-supervised":[41],"reduce":[43,145],"requirement":[45],"data,":[49,197],"however,":[50],"problems":[52],"overhead":[55],"are":[59,111,133,297],"rarely":[60],"addressed.":[61],"This":[62],"paper":[63],"proposes":[64],"a":[65,79,84,96,115,120,138,182,234,247,257,280],"method":[66,286],"address":[68,228],"challenges":[71],"image":[74],"classification":[75],"task.":[76],"We":[77,227,244],"introduce":[78],"transfer":[80,186],"approach":[82,161],"target":[85],"data":[86,204,225],"set,":[87],"in":[88,187],"we":[90,144,198],"take":[91],"learned":[93,109,175],"features":[94,110],"from":[95,177,202,208],"self-supervised":[97,179,210,236],"model":[98,180,211,238],"after":[99],"minimizing":[100],"its":[101],"parameters":[102,292],"by":[103,119,147,172,205,232],"removing":[104],"final":[106],"layer.":[107],"The":[108,159,167,295],"then":[112],"fed":[113],"into":[114],"classifier,":[117],"followed":[118],"multi-layer":[121],"perceptron":[122],"(MLP),":[123],"where":[124],"hyperparameters":[126],"both":[128],"MLP":[132],"automatically":[134],"tuned":[135],"(autotuned)":[136],"using":[137],"Bayesian":[139],"optimization":[140],"based":[141],"technique.":[142],"Further,":[143],"GFLOPs":[146],"limiting":[148],"search":[150,242],"space":[151],"hyperparameters,":[154],"not":[155],"performance.":[158],"proposed":[160,189,285],"effectively":[162],"deals":[163],"above":[165],"first":[168],"challenge":[169,231],"is":[170],"addressed":[171],"utilizing":[173,233],"representations":[176],"as":[181,254],"foundation":[183],"knowledge":[185,207],"model.":[190],"Rather":[191],"than":[192],"relying":[193],"solely":[194],"on":[195],"employ":[199],"insights":[201],"unlabeled":[203],"transferring":[206],"task":[214],"at":[215,299],"hand,":[216],"hence":[217],"reducing":[218],"cost":[220],"effort":[222],"associated":[223],"annotation.":[226],"second":[230],"minimized":[235],"backbone":[237],"constraining":[240],"space.":[243],"experiment":[245],"wide":[248],"variety":[249,281],"benchmark":[251],"datasets,":[252],"such":[253],"large":[258],"number":[259],"small-sized":[261],"images":[262,268,278],"(CIFAR-10":[263],"CIFAR-100),":[265],"fewer":[266,291],"large-sized":[267,277],"(Oxford-IIIT":[269],"Pet":[270],"Dataset":[271],"Oxford":[273],"102":[274],"flowers),":[275],"classes":[283],"(Caltech101).The":[284],"outperforms":[287],"state-of-theart":[289],"GFLOPs.":[294],"codes":[296],"available":[298],"<uri":[300],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[301],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/jk452/minimized-parameter-overload</uri>":[302]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}