{"id":"https://openalex.org/W4414359978","doi":"https://doi.org/10.24963/ijcai.2025/179","title":"Squeezing Context into Patches: Towards Memory-Efficient Ultra-High Resolution Semantic Segmentation","display_name":"Squeezing Context into Patches: Towards Memory-Efficient Ultra-High Resolution Semantic Segmentation","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359978","doi":"https://doi.org/10.24963/ijcai.2025/179"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/179","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":null,"display_name":"Wang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang Liu","raw_affiliation_strings":["Hunan Univercity"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan Univercity","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011401698","display_name":"Puhong Duan","orcid":"https://orcid.org/0000-0001-5066-4399"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Puhong Duan","raw_affiliation_strings":["Hunan Univercity"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan Univercity","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057514965","display_name":"Xudong Kang","orcid":"https://orcid.org/0000-0002-3807-2531"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xudong Kang","raw_affiliation_strings":["Hunan Univercity"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan Univercity","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067097659","display_name":"Shutao Li","orcid":"https://orcid.org/0000-0002-0585-9848"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shutao Li","raw_affiliation_strings":["Hunan Univercity"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan Univercity","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1603","last_page":"1611"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9106000065803528,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9106000065803528,"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/segmentation","display_name":"Segmentation","score":0.8194000124931335},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6402999758720398},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6392999887466431},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6118000149726868},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.595300018787384},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.4848000109195709},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.47679999470710754},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4487999975681305},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4174000024795532}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8194000124931335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7678999900817871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6615999937057495},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6402999758720398},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6392999887466431},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6118000149726868},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.595300018787384},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.4848000109195709},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.47679999470710754},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4487999975681305},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42419999837875366},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.38420000672340393},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3294999897480011},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.31839999556541443},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2888999879360199},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.2775999903678894},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/179","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Segmenting":[0],"ultra-high-resolution":[1],"(UHR)":[2],"images":[3],"poses":[4],"a":[5,16,23,32,63,87,93,118],"significant":[6],"challenge":[7],"due":[8],"to":[9,15,35,99,110,126],"constraints":[10],"on":[11,158],"GPU":[12],"memory,":[13],"leading":[14],"trade-off":[17],"between":[18],"detailed":[19],"local":[20,37,73,82,105,121,132],"information":[21,71,85],"and":[22,38,53,83],"comprehensive":[24],"contextual":[25,39,84],"understanding.":[26],"Current":[27],"UHR":[28,59,162,172],"methods":[29],"often":[30],"employ":[31],"multi-branch":[33],"encoder":[34],"handle":[36],"information,":[40],"which":[41],"can":[42],"be":[43],"memory-intensive.":[44],"To":[45],"address":[46],"the":[47,79,147,152,181],"need":[48],"for":[49],"both":[50],"high":[51],"accuracy":[52,174],"low":[54],"memory":[55,178],"usage":[56],"in":[57],"processing":[58,80],"images,":[60],"we":[61,91,116],"introduce":[62,92],"memory-efficient":[64],"semantic":[65],"segmentation":[66,108,128,163,173],"approach":[67,136,170],"by":[68,130],"squeezing":[69,95],"context":[70,94,102],"into":[72,104],"patches":[74],"(SCPSeg).":[75],"Our":[76],"method":[77,157],"integrates":[78],"of":[81,154],"within":[86,139],"single-branch":[88],"encoder.":[89],"Specifically,":[90],"module":[96],"(CSM)":[97],"designed":[98],"compress":[100],"global":[101],"details":[103],"patches,":[106],"enabling":[107],"networks":[109],"perceive":[111],"broader":[112],"image":[113],"contexts.":[114],"Additionally,":[115],"propose":[117],"super-resolution":[119],"guided":[120],"feature":[122,133],"alignment":[123],"(LFA)":[124],"technique":[125],"improve":[127],"precision":[129],"aligning":[131],"relationships.":[134],"This":[135],"calculates":[137],"similarities":[138],"sliding":[140],"windows,":[141],"avoiding":[142],"heavy":[143],"computational":[144],"costs":[145],"during":[146,180],"training":[148],"phase.":[149],"We":[150],"evaluate":[151],"effectiveness":[153],"our":[155,169],"proposed":[156],"four":[159],"widely":[160],"used":[161],"benchmarks.":[164],"Experimental":[165],"results":[166],"demonstrate":[167],"that":[168],"enhances":[171],"without":[175],"incurring":[176],"additional":[177],"overhead":[179],"inference":[182],"stage.":[183],"The":[184],"code":[185],"is":[186],"available":[187],"at":[188],"https://github.com/StuLiu/SCPSeg.":[189]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}