{"id":"https://openalex.org/W7164821824","doi":"https://doi.org/10.1145/3805622.3810873","title":"CPD: Distilling Semantics in Feature Space via Class-Projection Interaction","display_name":"CPD: Distilling Semantics in Feature Space via Class-Projection Interaction","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164821824","doi":"https://doi.org/10.1145/3805622.3810873"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810873","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810873","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810873","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100633632","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0003-0098-5359"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingbin Wang","raw_affiliation_strings":["University of Electronic Science and Technology of China, ChengDu, China"],"raw_orcid":"https://orcid.org/0009-0001-8351-073X","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, ChengDu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043163390","display_name":"Jielei Wang","orcid":"https://orcid.org/0000-0003-2882-7053"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jielei Wang","raw_affiliation_strings":["University of Electronic Science and Technology of China, ChengDu, China"],"raw_orcid":"https://orcid.org/0000-0003-2882-7053","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, ChengDu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008716657","display_name":"Qianxin Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianxin Xia","raw_affiliation_strings":["University of Electronic Science and Technology of China, ChengDu, China"],"raw_orcid":"https://orcid.org/0009-0007-7845-6349","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, ChengDu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108993626","display_name":"Xuewan He","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuewan He","raw_affiliation_strings":["University of Electronic Science and Technology of China, ChengDu, China"],"raw_orcid":"https://orcid.org/0009-0002-5273-1318","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, ChengDu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000444026","display_name":"Guoming Lu","orcid":"https://orcid.org/0000-0001-7477-5800"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoming Lu","raw_affiliation_strings":["University of Electronic Science and Technology of China, ChengDu, China"],"raw_orcid":"https://orcid.org/0000-0001-7477-5800","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, ChengDu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93553635,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1563","last_page":"1567"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.30480000376701355,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.30480000376701355,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.27549999952316284,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.07940000295639038,"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/feature","display_name":"Feature (linguistics)","score":0.617900013923645},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6093000173568726},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5843999981880188},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5626000165939331},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5188999772071838},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5006999969482422},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.4950000047683716},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41019999980926514},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.37630000710487366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7229999899864197},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.617900013923645},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6093000173568726},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5843999981880188},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5626000165939331},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5188999772071838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5138000249862671},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5006999969482422},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4950000047683716},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4300999939441681},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.37630000710487366},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26100000739097595},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2535000145435333},{"id":"https://openalex.org/C207363949","wikidata":"https://www.wikidata.org/wiki/Q462915","display_name":"Visual space","level":3,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810873","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810873","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810873","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810873","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7748889327049255,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2026498605","https://openalex.org/W2108598243","https://openalex.org/W2128728535","https://openalex.org/W2737258237","https://openalex.org/W2962858109","https://openalex.org/W3014721989","https://openalex.org/W3138516171","https://openalex.org/W3151130473","https://openalex.org/W4226426325","https://openalex.org/W4386072392","https://openalex.org/W4390873054","https://openalex.org/W4404212170","https://openalex.org/W4415797084","https://openalex.org/W4415797386","https://openalex.org/W7133215549","https://openalex.org/W7133245318","https://openalex.org/W7160029582"],"related_works":[],"abstract_inverted_index":{"Vision":[0],"Foundation":[1],"Models":[2],"(VFMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"performance":[7],"across":[8],"various":[9],"visual":[10],"downstream":[11],"tasks.":[12],"To":[13],"transfer":[14],"their":[15],"strong":[16],"representation":[17],"ability":[18],"into":[19,126],"lightweight":[20],"CNNs,":[21],"knowledge":[22],"distillation":[23,32],"serves":[24],"as":[25],"a":[26,80,105,139],"promising":[27],"approach.":[28],"However,":[29],"existing":[30],"feature-based":[31],"methods":[33],"typically":[34],"perform":[35],"alignment":[36,86],"in":[37],"spatial":[38],"or":[39],"channel":[40],"dimensions,":[41],"often":[42],"neglecting":[43],"the":[44,61,67,89,93,98,127,160,185,210],"explicit":[45,116,194],"semantic":[46,52,85,196],"meaning":[47],"of":[48,95],"intermediate":[49,191],"features.":[50],"This":[51],"agnosticism":[53],"leads":[54],"to":[55,131,159,163,184,188],"inefficient":[56],"transfer,":[57],"where":[58,155,179],"students":[59],"mimic":[60],"teacher\u2019s":[62],"activation":[63],"patterns":[64],"without":[65],"grasping":[66],"underlying":[68],"class-discriminative":[69],"logic.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74,137],"propose":[75],"Class-space":[76],"Projection":[77],"Distillation":[78],"(CPD),":[79],"novel":[81],"framework":[82],"that":[83,144,206],"enforces":[84],"directly":[87,189],"within":[88],"feature":[90,122,161],"space.":[91],"At":[92],"core":[94],"CPD":[96,207],"is":[97],"Class-Projection":[99],"Attention":[100],"(CPA)":[101],"module,":[102],"which":[103],"introduces":[104],"parallel":[106],"dual-stream":[107],"interaction":[108],"mechanism:":[109],"it":[110],"complements":[111],"standard":[112],"spatial-texture":[113],"retention":[114],"with":[115],"class-semantic":[117],"alignment.":[118],"Specifically,":[119],"CPA":[120],"projects":[121],"queries":[123],"and":[124,171,203],"keys":[125],"global":[128],"class":[129,169,186],"space":[130],"generate":[132,190],"Semantic":[133],"Consistency":[134],"Maps.":[135],"Crucially,":[136],"design":[138],"versatile":[140],"value":[141],"projection":[142],"strategy":[143],"leverages":[145],"these":[146],"maps":[147],"for":[148],"two":[149],"distinct":[150],"purposes:":[151],"(1)":[152],"Semantic-Guided":[153],"Fusion,":[154],"values":[156,180],"are":[157,181],"projected":[158,183],"dimension":[162,187],"refine":[164],"student":[165],"representations":[166],"based":[167],"on":[168,200],"consistency;":[170],"(2)":[172],"Generative":[173],"Class":[174],"Activation":[175],"Map":[176],"(CAM)":[177],"Supervision,":[178],"parallelly":[182],"CAMs,":[192],"enforcing":[193],"pixel-level":[195],"constraints.":[197],"Extensive":[198],"experiments":[199],"CIFAR-100,":[201],"Tiny-ImageNet,":[202],"ImageNet-1K":[204],"demonstrate":[205],"effectively":[208],"bridges":[209],"architectural":[211],"gap,":[212],"consistently":[213],"outperforming":[214],"state-of-the-art":[215],"methods.":[216]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}