{"id":"https://openalex.org/W7138048617","doi":"https://doi.org/10.1609/aaai.v40i16.38319","title":"Beyond Predictive Resampling: Learning Input-Agnostic Downsampling for Efficient Aligned Vision Recognition","display_name":"Beyond Predictive Resampling: Learning Input-Agnostic Downsampling for Efficient Aligned Vision Recognition","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138048617","doi":"https://doi.org/10.1609/aaai.v40i16.38319"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i16.38319","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38319","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i16.38319","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129701097","display_name":"Kai Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kai Zhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129655496","display_name":"Liting Ruan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liting Ruan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129640922","display_name":"Haoran Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoran Jiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129647837","display_name":"Xiaoqiang Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoqiang Zhu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129720685","display_name":"Xianchao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianchao Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129733343","display_name":"Dan Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Zeng","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5129701097"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34004474,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"16","first_page":"13181","last_page":"13189"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.8277000188827515,"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/T11448","display_name":"Face recognition and analysis","score":0.8277000188827515,"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/T10828","display_name":"Biometric Identification and Security","score":0.08079999685287476,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10057","display_name":"Face and Expression Recognition","score":0.026000000536441803,"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/upsampling","display_name":"Upsampling","score":0.9232000112533569},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5462999939918518},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.5442000031471252},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.5008000135421753},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4821999967098236},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4724999964237213},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4659000039100647},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4535999894142151},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.43950000405311584}],"concepts":[{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.9232000112533569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7702000141143799},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7078999876976013},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5462999939918518},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.5442000031471252},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.5008000135421753},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49950000643730164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4821999967098236},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4724999964237213},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4535999894142151},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.43950000405311584},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43220001459121704},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.40610000491142273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37689998745918274},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C200331156","wikidata":"https://www.wikidata.org/wiki/Q506041","display_name":"Jacobian matrix and determinant","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3001999855041504},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.2953999936580658},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27000001072883606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i16.38319","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38319","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i16.38319","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38319","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.45722538232803345,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Images":[0],"are":[1,13,19],"typically":[2],"sampled":[3],"on":[4,46,152,210],"a":[5,102,107,139,158,232],"uniform":[6],"grid,despite":[7],"their":[8,67],"non-uniform":[9],"information":[10],"distribution\u2014some":[11],"regions":[12],"rich":[14],"in":[15,28,93],"content":[16],"while":[17],"others":[18],"not.":[20],"The":[21,175],"mismatch":[22],"leads":[23],"to":[24,53,61,145,171,195],"inefficient":[25],"computation":[26],"allocation":[27],"deep":[29],"learning":[30],"models.":[31],"To":[32],"address":[33],"this,":[34],"recent":[35],"studies":[36],"have":[37],"proposed":[38],"predictive":[39,239],"downsampling":[40,142,240],"methodsthat":[41],"adaptively":[42],"downsample":[43],"images":[44],"based":[45],"predicted":[47],"per-pixel":[48],"importance,":[49,64],"allocating":[50],"more":[51,181,185],"pixels":[52],"informative":[54],"areas.":[55],"However,these":[56],"methods":[57],"require":[58],"high-resolution":[59,82],"processing":[60],"accurately":[62],"estimate":[63],"which":[65],"undermines":[66],"efficiency:the":[68],"prediction":[69,84],"itself":[70],"must":[71],"process":[72],"the":[73,78,164,168,172,189,198],"full-resolution":[74],"image,consuming":[75],"most":[76],"of":[77,150],"computational":[79,225],"budget.":[80],"This":[81,131],"importance":[83,154],"is":[85,178],"necessary":[86],"because":[87],"each":[88],"input":[89,123],"may":[90],"differ":[91],"significantly":[92,233],"structure":[94,128],"and":[95,105,119,201,204,216],"content.":[96],"In":[97],"this":[98],"paper,":[99],"we":[100,156,187],"take":[101],"different":[103],"approach":[104],"introduce":[106,157],"learn-to-downsample":[108],"paradigmtailored":[109],"for":[110],"aligned":[111,212],"vision":[112],"recognition":[113,118,213],"tasks,":[114,214],"such":[115],"as":[116],"face":[117,215],"palmprint":[120,217],"recognition,":[121,218],"where":[122],"alignment":[124,132],"ensures":[125,133],"consistent":[126],"spatial":[127,165],"across":[129,136],"images.":[130],"structural":[134],"consistency":[135],"images,":[137],"allowing":[138],"shared,":[140],"input-agnostic":[141],"template":[143],"applicable":[144],"all":[146],"inputs.":[147],"Furthermore,":[148],"instead":[149],"relying":[151],"implicit":[153],"maps,":[155],"flow-based":[159],"representation":[160,177],"that":[161,220],"explicitly":[162],"models":[163],"warping":[166],"from":[167],"original":[169],"image":[170],"downsampled":[173],"version.":[174],"flow":[176,190],"not":[179],"only":[180],"efficient":[182],"but":[183],"also":[184],"controllable:":[186],"regularize":[188],"using":[191],"its":[192],"Jacobian":[193],"determinant":[194],"precisely":[196],"control":[197],"sampling":[199,206],"density":[200],"coverage,enabling":[202],"interpretable":[203],"tunable":[205],"patterns.":[207],"Extensive":[208],"experiments":[209],"two":[211],"demonstrate":[219],"our":[221],"method":[222],"substantially":[223],"reduces":[224],"cost":[226],"with":[227],"minimal":[228],"accuracy":[229],"degradation,":[230],"achieving":[231],"better":[234],"performance-efficiency":[235],"trade-off":[236],"than":[237],"existing":[238],"methods.":[241]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}