{"id":"https://openalex.org/W4415626466","doi":"https://doi.org/10.1109/tip.2025.3624626","title":"Unleashing the Power of Each Distilled Image","display_name":"Unleashing the Power of Each Distilled Image","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415626466","doi":"https://doi.org/10.1109/tip.2025.3624626","pmid":"https://pubmed.ncbi.nlm.nih.gov/41150227"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3624626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3624626","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5115593811","display_name":"Jingxuan Zhang","orcid":"https://orcid.org/0009-0000-8480-322X"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingxuan Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-8480-322X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101463900","display_name":"Zhihua Chen","orcid":"https://orcid.org/0000-0003-4496-1340"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihua Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4496-1340","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060490956","display_name":"Lei Dai","orcid":"https://orcid.org/0000-0002-9498-384X"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Dai","raw_affiliation_strings":["Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9498-384X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I143593769"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27500269,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"7050","last_page":"7064"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5981000065803528,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5981000065803528,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.03849999979138374,"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":0.03319999948143959,"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/overfitting","display_name":"Overfitting","score":0.6796000003814697},{"id":"https://openalex.org/keywords/distilled-water","display_name":"Distilled water","score":0.5156999826431274},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.507099986076355},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4977000057697296},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4390000104904175},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4366999864578247},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39719998836517334},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.36800000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6827999949455261},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6796000003814697},{"id":"https://openalex.org/C2779429693","wikidata":"https://www.wikidata.org/wiki/Q274959","display_name":"Distilled water","level":2,"score":0.5156999826431274},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.507099986076355},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4977000057697296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48260000348091125},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4390000104904175},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39719998836517334},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.33899998664855957},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2948000133037567},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2025.3624626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3624626","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:41150227","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41150227","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4207769417","display_name":null,"funder_award_id":"62306113","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7585897070","display_name":null,"funder_award_id":"62272164","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7866928754","display_name":null,"funder_award_id":"62572188","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1861492603","https://openalex.org/W1997865285","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2765793020","https://openalex.org/W2806070179","https://openalex.org/W2963163009","https://openalex.org/W3105146463","https://openalex.org/W4225385394","https://openalex.org/W4288325606","https://openalex.org/W4306168147","https://openalex.org/W4312252393","https://openalex.org/W4312349930","https://openalex.org/W4312412605","https://openalex.org/W4319300193","https://openalex.org/W4386065613","https://openalex.org/W4386075990","https://openalex.org/W4390871903","https://openalex.org/W4390872297","https://openalex.org/W4390872541","https://openalex.org/W4402667890","https://openalex.org/W4402715869","https://openalex.org/W4402727287","https://openalex.org/W4402772294","https://openalex.org/W4402915941","https://openalex.org/W4411948547"],"related_works":[],"abstract_inverted_index":{"Dataset":[0],"distillation":[1],"(DD)":[2],"aims":[3],"to":[4,26,125,143],"accelerate":[5],"the":[6,21,29,38,45,56,61,79,92,119,127,145,181,189,205],"training":[7,129],"speed":[8],"of":[9,64,121,183,215],"neural":[10],"networks":[11],"(NNs)":[12],"by":[13,60,86,132,209],"synthesizing":[14],"a":[15,50,73,137,193,212],"reduced":[16],"dataset.":[17,152],"NNs":[18],"trained":[19],"on":[20,37,162,166,188],"smaller":[22],"dataset":[23,48,52,140,148,191],"are":[24,84,115,159],"expected":[25],"obtain":[27],"almost":[28],"same":[30],"test":[31],"set":[32],"accuracy":[33,214],"as":[34,49],"they":[35],"do":[36],"larger":[39],"one.":[40],"Previous":[41],"DD":[42,75],"research":[43],"treated":[44],"obtained":[46],"distilled":[47,66,82,113,147,151,198,213],"regular":[51],"for":[53,111],"training,":[54],"neglecting":[55],"overfitting":[57],"issue":[58],"caused":[59,131],"limited":[62],"number":[63],"original":[65,146],"images.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71,135],"propose":[72],"new":[74,154],"paradigm.":[76],"Specifically,":[77],"in":[78],"deployment":[80],"stage,":[81],"images":[83,199],"augmented":[85,122,150],"amplifying":[87],"their":[88],"local":[89],"information":[90],"since":[91],"teacher":[93],"network":[94],"can":[95],"produce":[96],"diverse":[97,108],"supervision":[98],"signals":[99],"when":[100],"receiving":[101],"inputs":[102],"from":[103],"different":[104],"regions.":[105],"Efficient":[106],"and":[107,149,157,178,196],"augmentation":[109],"methods":[110],"each":[112],"image":[114],"devised,":[116],"while":[117],"ensuring":[118],"authenticity":[120],"samples.":[123],"Additionally,":[124],"alleviate":[126],"increased":[128],"cost":[130],"data":[133],"augmentation,":[134],"design":[136],"bi-directional":[138],"dynamic":[139],"pruning":[141,155],"technique":[142],"prune":[144],"A":[153],"strategy":[156],"scheduling":[158],"proposed":[160],"based":[161],"experimental":[163],"findings.":[164],"Experiments":[165],"9":[167],"benchmark":[168],"datasets":[169],"(CIFAR10,":[170],"CIFAR100,":[171],"ImageWoof,":[172],"ImageCat,":[173],"ImageFruit,":[174],"ImageNette,":[175],"ImageNet10,":[176],"ImageNet100":[177],"ImageNet1K)":[179],"demonstrate":[180],"effectiveness":[182],"our":[184,202],"approach.":[185],"For":[186],"instance,":[187],"ImageNet1K":[190],"with":[192],"ResNet18":[194],"architecture":[195],"50":[197],"per":[200],"class,":[201],"algorithm":[203,208],"surpasses":[204],"second-ranked":[206],"MiniMax":[207],"7.6%,":[210],"achieving":[211],"66.2%.":[216]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-29T00:00:00"}