{"id":"https://openalex.org/W7131093806","doi":"https://doi.org/10.1109/iccvw69036.2025.00330","title":"FDAL: Leveraging Feature Distillation for Efficient and Task-Aware Active Learning","display_name":"FDAL: Leveraging Feature Distillation for Efficient and Task-Aware Active Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131093806","doi":"https://doi.org/10.1109/iccvw69036.2025.00330"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5057223184","display_name":"Rebati Gaire","orcid":"https://orcid.org/0000-0001-8413-3393"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rebati Gaire","raw_affiliation_strings":["University of Illinois Chicago,Chicago,Illinois"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Chicago,Chicago,Illinois","institution_ids":["https://openalex.org/I39422238","https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077392159","display_name":"Arman Roohi","orcid":"https://orcid.org/0000-0002-0900-8768"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arman Roohi","raw_affiliation_strings":["University of Illinois Chicago,Chicago,Illinois"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Chicago,Chicago,Illinois","institution_ids":["https://openalex.org/I39422238","https://openalex.org/I40347166"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.624,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8918297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3162","last_page":"3169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9670000076293945,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9670000076293945,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.004399999976158142,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.003599999938160181,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6093000173568726},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5717999935150146},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.5264999866485596},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5123000144958496},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5084999799728394},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.504800021648407},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4966999888420105},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.48980000615119934},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4745999872684479},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4361000061035156}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79830002784729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6542999744415283},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6538000106811523},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6093000173568726},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5717999935150146},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.5264999866485596},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5123000144958496},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5084999799728394},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.504800021648407},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4966999888420105},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4745999872684479},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4361000061035156},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.41339999437332153},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3732999861240387},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.33959999680519104},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.3264000117778778},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3199999928474426},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3037000000476837},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1679974410","display_name":"CAREER: Elastic Intermittent Computation Enabling Batteryless Edge Intelligence","funder_award_id":"2504839","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2294370754","https://openalex.org/W2300242332","https://openalex.org/W2407386500","https://openalex.org/W2798820905","https://openalex.org/W2956371155","https://openalex.org/W2986514296","https://openalex.org/W2997006708","https://openalex.org/W3094502228","https://openalex.org/W3174010726","https://openalex.org/W3174894125","https://openalex.org/W3179550234","https://openalex.org/W3205626500","https://openalex.org/W4200492619","https://openalex.org/W4385490607","https://openalex.org/W4386065753","https://openalex.org/W4386083031","https://openalex.org/W4392822145","https://openalex.org/W4392943618","https://openalex.org/W4402835359","https://openalex.org/W4403600599","https://openalex.org/W4414197578"],"related_works":[],"abstract_inverted_index":{"Active":[0],"learning":[1,71,96],"(AL)":[2],"offers":[3],"a":[4,81,107],"promising":[5],"strategy":[6,127],"for":[7,122],"reducing":[8],"annotation":[9,163],"costs":[10],"by":[11],"selectively":[12],"querying":[13],"informative":[14,119],"samples.":[15],"However,":[16],"its":[17],"deployment":[18],"on":[19,97,139,170],"edge":[20],"devices":[21],"remains":[22],"fundamentally":[23],"limited.":[24],"In":[25],"such":[26],"resource-constrained":[27],"environments,":[28],"models":[29],"must":[30],"be":[31],"highly":[32],"compact":[33],"to":[34,55,63,91,117],"meet":[35],"strict":[36],"compute,":[37],"memory,":[38],"and":[39,52,94,134,142,162],"energy":[40],"budgets.":[41,164],"These":[42],"lightweight":[43,108],"models,":[44],"though":[45],"efficient,":[46],"suffer":[47],"from":[48,114],"limited":[49,160],"representational":[50],"capacity":[51],"are":[53],"ill-equipped":[54],"support":[56],"existing":[57],"AL":[58,87,150],"methods,":[59,151],"which":[60],"assume":[61],"access":[62],"high-capacity":[64],"networks":[65],"capable":[66],"of":[67,182],"modeling":[68],"uncertainty":[69],"or":[70],"expressive":[72],"acquisition":[73],"functions.":[74],"To":[75],"address":[76],"this,":[77],"we":[78],"introduce":[79],"FDAL,":[80],"unified":[82],"framework":[83],"that":[84,145],"couples":[85],"task-aware":[86,101],"with":[88,155,172],"feature-distilled":[89],"training":[90],"enable":[92],"efficient":[93],"accurate":[95],"resource-limited":[98],"devices.":[99],"A":[100],"sampler":[102],"network,":[103],"trained":[104],"adversarially":[105],"alongside":[106],"task":[109,132],"model,":[110],"exploits":[111],"refined":[112],"features":[113],"feature":[115],"distillation":[116],"prioritize":[118],"unlabeled":[120],"instances":[121],"annotation.":[123],"This":[124],"joint":[125],"optimization":[126],"ensures":[128],"tight":[129],"coupling":[130],"between":[131],"utility":[133],"sampling":[135],"efficacy.":[136],"Extensive":[137],"experiments":[138],"SVHN,":[140],"CIFAR-10,":[141],"CIFAR-100":[143],"demonstrate":[144],"FDAL":[146,166],"consistently":[147],"outperforms":[148],"state-of-the-art":[149],"achieving":[152],"competitive":[153],"accuracy":[154,169],"significantly":[156],"fewer":[157],"labels":[158],"under":[159],"compute":[161],"Notably,":[165],"achieves":[167],"78.5%":[168],"CIFAR-10":[171],"only":[173],"30%":[174],"labeled":[175],"data,":[176],"matching":[177],"the":[178],"fully":[179],"supervised":[180],"baseline":[181],"78.38%.":[183],"The":[184],"code":[185],"is":[186],"made":[187],"publicly":[188],"available":[189],"at":[190],"https://github.com/rrgaire/FDALforreproducibilityandfutureresearch.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2026-02-24T00:00:00"}