{"id":"https://openalex.org/W4408355043","doi":"https://doi.org/10.1109/icassp49660.2025.10890489","title":"Cross-Layer Cache Aggregation for Token Reduction in Ultra-Fine-Grained Image Recognition","display_name":"Cross-Layer Cache Aggregation for Token Reduction in Ultra-Fine-Grained Image Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355043","doi":"https://doi.org/10.1109/icassp49660.2025.10890489"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890489","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5087804607","display_name":"Edwin Arkel Rios","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Edwin Arkel Rios","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115756444","display_name":"Jansen Christopher Yuanda","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jansen Christopher Yuanda","raw_affiliation_strings":["National Tsing Hua University,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115756445","display_name":"Vincent Leon Ghanz","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Vincent Leon Ghanz","raw_affiliation_strings":["National Tsing Hua University,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103114290","display_name":"Cheng\u2010Wei Yu","orcid":"https://orcid.org/0000-0002-4832-9038"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-Wei Yu","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013913342","display_name":"Bo\u2010Cheng Lai","orcid":"https://orcid.org/0000-0002-9729-5196"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Bo-Cheng Lai","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113057018","display_name":"Min-Chun Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Min-Chun Hu","raw_affiliation_strings":["National Tsing Hua University,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5087804607"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07272638,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9840999841690063,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9840999841690063,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9487000107765198,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9484999775886536,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.696880578994751},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.6149035692214966},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6144208908081055},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5764856338500977},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5282501578330994},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3013879656791687},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.15419617295265198},{"id":"https://openalex.org/keywords/nanotechnology","display_name":"Nanotechnology","score":0.08953386545181274}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.696880578994751},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6149035692214966},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6144208908081055},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5764856338500977},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5282501578330994},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3013879656791687},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.15419617295265198},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.08953386545181274},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890489","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2963446712","https://openalex.org/W3035422918","https://openalex.org/W3118432192","https://openalex.org/W3139434170","https://openalex.org/W3145450063","https://openalex.org/W3159481202","https://openalex.org/W3203876692","https://openalex.org/W3213192039","https://openalex.org/W3216553632","https://openalex.org/W4304084267","https://openalex.org/W4312340826","https://openalex.org/W4312453657","https://openalex.org/W4312530435","https://openalex.org/W4312872526","https://openalex.org/W4313156423","https://openalex.org/W4319068822","https://openalex.org/W4360770920","https://openalex.org/W4379983950","https://openalex.org/W4392208008","https://openalex.org/W4411244874","https://openalex.org/W6729059855","https://openalex.org/W6747381837","https://openalex.org/W6767750063","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6794559225","https://openalex.org/W6796494063","https://openalex.org/W6811032435","https://openalex.org/W6846007759","https://openalex.org/W6846577953","https://openalex.org/W6856857450"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W4285141722","https://openalex.org/W4387768015"],"abstract_inverted_index":{"Ultra-fine-grained":[0],"image":[1,175],"recognition":[2,53],"(UFGIR)":[3],"is":[4,111,220],"a":[5,13,30,36,62,129,136,213],"challenging":[6],"task":[7,57,72],"that":[8],"involves":[9],"classifying":[10,20,27],"images":[11],"within":[12,29],"macro-category.":[14],"While":[15],"traditional":[16],"FGIR":[17],"deals":[18],"with":[19],"different":[21],"species,":[22],"UFGIR":[23,197],"goes":[24],"beyond":[25],"by":[26,121,198],"sub-categories":[28],"species":[31],"such":[32,82],"as":[33,83,106],"cultivars":[34],"of":[35,43,67,99,118,124,180,192,207],"plant.":[37],"In":[38],"recent":[39],"times":[40],"the":[41,90,107,116,122,178,181,190,200],"usage":[42,123],"Vision":[44],"Transformer-based":[45],"backbones":[46],"has":[47],"allowed":[48],"methods":[49],"to":[50,88,97,114,140,188,203,209,216],"obtain":[51],"outstanding":[52],"performances":[54],"in":[55,65,148],"this":[56,59,71],"but":[58],"comes":[60],"at":[61],"significant":[63],"cost":[64,195],"terms":[66],"computation":[68],"specially":[69,105],"since":[70],"significantly":[73],"benefits":[74],"from":[75,145],"incorporating":[76],"higher":[77],"resolution":[78],"images.":[79],"Therefore,":[80,113],"techniques":[81],"token":[84,108,125,167],"reduction":[85,126,168],"have":[86],"emerged":[87],"reduce":[89],"computational":[91],"cost.":[92],"However,":[93],"dropping":[94],"tokens":[95,202],"leads":[96],"loss":[98,117],"essential":[100],"information":[101,119,144],"for":[102,196],"fine-grained":[103],"categories,":[104],"keep":[109,171],"rate":[110],"reduced.":[112],"counteract":[115],"brought":[120],"we":[127],"propose":[128],"novel":[130],"Cross-Layer":[131,137],"Aggregation":[132],"Classification":[133],"Head":[134],"and":[135,142,173,185],"Cache":[138],"mechanism":[139],"recover":[141],"access":[143],"previous":[146],"layers":[147],"later":[149],"locations.":[150],"Extensive":[151],"experiments":[152],"covering":[153],"more":[154],"than":[155],"2000":[156],"runs":[157],"across":[158],"diverse":[159],"settings":[160],"including":[161],"5":[162,170],"datasets,":[163],"9":[164],"backbones,":[165],"7":[166],"methods,":[169],"rates,":[172],"2":[174],"sizes":[176],"demonstrate":[177],"effectiveness":[179],"proposed":[182],"plug-and-play":[183],"modules":[184],"allow":[186],"us":[187],"push":[189],"boundaries":[191],"accuracy":[193,215],"vs":[194],"reducing":[199],"kept":[201],"extremely":[204],"low":[205],"ratios":[206],"up":[208],"10%":[210],"while":[211],"maintaining":[212],"competitive":[214],"state-of-the-art":[217],"models.":[218],"Code":[219],"available":[221],"at:":[222],"https://github.com/arkel23/CLCA":[223]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}
