{"id":"https://openalex.org/W4414360037","doi":"https://doi.org/10.24963/ijcai.2025/257","title":"Brain-Inspired Stepwise Patch Merging for Vision Transformers","display_name":"Brain-Inspired Stepwise Patch Merging for Vision Transformers","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360037","doi":"https://doi.org/10.24963/ijcai.2025/257"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/257","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/257","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":"https://openalex.org/A5060962435","display_name":"Yonghao Yu","orcid":"https://orcid.org/0000-0001-8414-4666"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210164150","display_name":"Shanghai Center for Brain Science and Brain-Inspired Technology","ror":"https://ror.org/0551a0y31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210164150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghao Yu","raw_affiliation_strings":["Brain-inspired Cognitive AI Lab, Institute of Automation, Chinese Academy of Sciences","School of Artificial Intelligence, University of Chinese Academy of Sciences","State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brain-inspired Cognitive AI Lab, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology","institution_ids":["https://openalex.org/I4210097554","https://openalex.org/I4210164150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016421437","display_name":"Dongcheng Zhao","orcid":"https://orcid.org/0000-0001-5280-8683"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210132266","display_name":"The Society for Post-Acute and Long-Term Care Medicine","ror":"https://ror.org/03zpeyw73","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210132266"]},{"id":"https://openalex.org/I4210164150","display_name":"Shanghai Center for Brain Science and Brain-Inspired Technology","ror":"https://ror.org/0551a0y31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210164150"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Dongcheng Zhao","raw_affiliation_strings":["Brain-inspired Cognitive AI Lab, Institute of Automation, Chinese Academy of Sciences","Center for Long-term AI","State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brain-inspired Cognitive AI Lab, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Center for Long-term AI","institution_ids":["https://openalex.org/I4210132266"]},{"raw_affiliation_string":"State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology","institution_ids":["https://openalex.org/I4210097554","https://openalex.org/I4210164150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075865717","display_name":"Guobin Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210164150","display_name":"Shanghai Center for Brain Science and Brain-Inspired Technology","ror":"https://ror.org/0551a0y31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210164150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guobin Shen","raw_affiliation_strings":["Brain-inspired Cognitive AI Lab, Institute of Automation, Chinese Academy of Sciences","School of Future Technology, University of Chinese Academy of Sciences","State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brain-inspired Cognitive AI Lab, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Future Technology, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology","institution_ids":["https://openalex.org/I4210097554","https://openalex.org/I4210164150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048906374","display_name":"Yiting Dong","orcid":"https://orcid.org/0000-0002-8405-3139"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210164150","display_name":"Shanghai Center for Brain Science and Brain-Inspired Technology","ror":"https://ror.org/0551a0y31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210164150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiting Dong","raw_affiliation_strings":["Brain-inspired Cognitive AI Lab, Institute of Automation, Chinese Academy of Sciences","School of Future Technology, University of Chinese Academy of Sciences","State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brain-inspired Cognitive AI Lab, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Future Technology, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology","institution_ids":["https://openalex.org/I4210097554","https://openalex.org/I4210164150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108421411","display_name":"Yi Zeng","orcid":"https://orcid.org/0000-0002-1357-7998"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210132266","display_name":"The Society for Post-Acute and Long-Term Care Medicine","ror":"https://ror.org/03zpeyw73","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210132266"]},{"id":"https://openalex.org/I4210164150","display_name":"Shanghai Center for Brain Science and Brain-Inspired Technology","ror":"https://ror.org/0551a0y31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210164150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yi Zeng","raw_affiliation_strings":["Brain-inspired Cognitive AI Lab, Institute of Automation, Chinese Academy of Sciences","Center for Long-term AI","School of Artificial Intelligence, University of Chinese Academy of Sciences","School of Future Technology, University of Chinese Academy of Sciences","State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brain-inspired Cognitive AI Lab, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Center for Long-term AI","institution_ids":["https://openalex.org/I4210132266"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"School of Future Technology, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology","institution_ids":["https://openalex.org/I4210097554","https://openalex.org/I4210164150"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":"2305","last_page":"2313"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9732000231742859,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9035999774932861,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5468999743461609},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5121999979019165},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3939000070095062},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.37470000982284546},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3328000009059906},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.328000009059906},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.32499998807907104},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.32280001044273376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6776999831199646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.597000002861023},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5468999743461609},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5121999979019165},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4300999939441681},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3328000009059906},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.32499998807907104},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C81147070","wikidata":"https://www.wikidata.org/wiki/Q1172449","display_name":"Encapsulation (networking)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2542000114917755},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/257","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/257","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,131],"hierarchical":[1,28],"architecture":[2,25],"has":[3,133],"become":[4],"a":[5,23,27,74],"mainstream":[6],"design":[7],"paradigm":[8],"for":[9,42],"Vision":[10],"Transformers":[11],"(ViTs),":[12],"with":[13,124],"Patch":[14,49],"Merging":[15,50],"serving":[16],"as":[17,112],"the":[18,33,54,101],"pivotal":[19],"component":[20],"that":[21,97,121],"transforms":[22],"columnar":[24],"into":[26],"one.":[29],"Drawing":[30],"inspiration":[31],"from":[32],"brain's":[34],"ability":[35,58],"to":[36,59],"integrate":[37],"global":[38],"and":[39,68,81,94,115],"local":[40,82],"information":[41],"comprehensive":[43],"visual":[44],"understanding,":[45],"we":[46],"propose":[47],"Stepwise":[48],"(SPM),":[51],"which":[52],"enhances":[53],"subsequent":[55],"attention":[56],"mechanism's":[57],"'see'":[60],"better.":[61],"SPM":[62,98,123],"consists":[63],"of":[64,103],"Multi-Scale":[65],"Aggregation":[66],"(MSA)":[67],"Guided":[69],"Local":[70],"Enhancement":[71],"(GLE)":[72],"striking":[73],"proper":[75],"balance":[76],"between":[77],"long-range":[78],"dependency":[79],"modeling":[80],"feature":[83],"enhancement.":[84],"Extensive":[85],"experiments":[86,119],"conducted":[87],"on":[88],"benchmark":[89],"datasets,":[90],"including":[91],"ImageNet-1K,":[92],"COCO,":[93],"ADE20K,":[95],"demonstrate":[96],"significantly":[99],"improves":[100],"performance":[102],"various":[104],"models,":[105],"particularly":[106],"in":[107],"dense":[108],"prediction":[109],"tasks":[110],"such":[111],"object":[113],"detection":[114],"semantic":[116],"segmentation.":[117],"Meanwhile,":[118],"show":[120],"combining":[122],"different":[125],"backbones":[126],"can":[127],"further":[128],"improve":[129],"performance.":[130],"code":[132],"been":[134],"released":[135],"at":[136],"https://github.com/Yonghao-Yu/StepwisePatchMerging.":[137]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
