{"id":"https://openalex.org/W4416831890","doi":"https://doi.org/10.1109/iccv51701.2025.00045","title":"A Hidden Stumbling Block in Generalized Category Discovery: Distracted Attention","display_name":"A Hidden Stumbling Block in Generalized Category Discovery: Distracted Attention","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416831890","doi":"https://doi.org/10.1109/iccv51701.2025.00045"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.14315","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034776297","display_name":"Qiang Xu","orcid":"https://orcid.org/0000-0002-4717-6025"},"institutions":[{"id":"https://openalex.org/I120825670","display_name":"Yunnan Normal University","ror":"https://ror.org/00sc9n023","country_code":"CN","type":"education","lineage":["https://openalex.org/I120825670"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiyu Xu","raw_affiliation_strings":["Yunnan Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yunnan Normal University","institution_ids":["https://openalex.org/I120825670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089910640","display_name":"Zhekai Hu","orcid":"https://orcid.org/0000-0001-5865-8225"},"institutions":[{"id":"https://openalex.org/I120825670","display_name":"Yunnan Normal University","ror":"https://ror.org/00sc9n023","country_code":"CN","type":"education","lineage":["https://openalex.org/I120825670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanxuan Hu","raw_affiliation_strings":["Yunnan Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yunnan Normal University","institution_ids":["https://openalex.org/I120825670"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yu Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Duan","raw_affiliation_strings":["Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014851312","display_name":"Ercheng Pei","orcid":"https://orcid.org/0000-0003-3582-6809"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ercheng Pei","raw_affiliation_strings":["Xi'an University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an University of Posts and Telecommunications","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049712745","display_name":"Yonghang Tai","orcid":"https://orcid.org/0000-0001-9186-475X"},"institutions":[{"id":"https://openalex.org/I120825670","display_name":"Yunnan Normal University","ror":"https://ror.org/00sc9n023","country_code":"CN","type":"education","lineage":["https://openalex.org/I120825670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghang Tai","raw_affiliation_strings":["Yunnan Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yunnan Normal University","institution_ids":["https://openalex.org/I120825670"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5034776297"],"corresponding_institution_ids":["https://openalex.org/I120825670"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35342719,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"405","last_page":"414"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.19269999861717224,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.19269999861717224,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.0934000015258789,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.08309999853372574,"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/security-token","display_name":"Security token","score":0.7975000143051147},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.7275000214576721},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7028999924659729},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.692300021648407},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5533000230789185},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5242999792098999},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.40630000829696655},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.35929998755455017}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7975000143051147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7304999828338623},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.7275000214576721},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7028999924659729},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.692300021648407},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5533000230789185},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5242999792098999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5134000182151794},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.40630000829696655},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37770000100135803},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32510000467300415},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccv51701.2025.00045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.14315","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.14315","pdf_url":"https://arxiv.org/pdf/2507.14315","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.14315","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.14315","pdf_url":"https://arxiv.org/pdf/2507.14315","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5349454775","display_name":null,"funder_award_id":"62201453","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generalized":[0],"Category":[1],"Discovery":[2],"(GCD)":[3],"aims":[4],"to":[5,47,64,82,161],"classify":[6],"unlabeled":[7,43],"data":[8],"from":[9,18],"both":[10],"known":[11,20],"and":[12,103],"unknown":[13],"categories":[14],"by":[15,87,124,131],"leveraging":[16],"knowledge":[17],"labeled":[19],"categories.":[21],"While":[22],"existing":[23,143],"methods":[24,145],"have":[25],"made":[26],"notable":[27],"progress,":[28],"they":[29],"often":[30],"overlook":[31],"a":[32,110,135],"hidden":[33],"stumbling":[34,71],"block":[35],"in":[36,54,109,177],"GCD:":[37],"distracted":[38],"attention.":[39],"Specifically,":[40],"when":[41],"processing":[42],"data,":[44],"models":[45],"tend":[46],"focus":[48,86],"not":[49],"only":[50],"on":[51,59],"key":[52],"objects":[53],"the":[55,84,126,166],"image":[56],"but":[57],"also":[58],"task-irrelevant":[60],"background":[61],"regions,":[62],"leading":[63],"suboptimal":[65],"feature":[66],"extraction.":[67],"To":[68],"remove":[69],"this":[70],"block,":[72],"we":[73],"propose":[74],"Attention":[75],"Focusing":[76],"(AF),":[77],"an":[78],"adaptive":[79],"mechanism":[80],"designed":[81],"sharpen":[83],"model's":[85],"pruning":[88],"non-informative":[89,122],"tokens.":[90],"AF":[91,133,158],"consists":[92],"of":[93],"two":[94],"simple":[95],"yet":[96],"effective":[97],"components:":[98],"Token":[99,104],"Importance":[100],"Measurement":[101],"(TIME)":[102],"Adaptive":[105],"Pruning":[106],"(TAP),":[107],"working":[108],"cascade.":[111],"TIME":[112],"quantifies":[113],"token":[114],"importance":[115,128],"across":[116],"multiple":[117],"scales,":[118],"while":[119],"TAP":[120],"prunes":[121],"tokens":[123],"utilizing":[125],"multi-scale":[127],"scores":[129],"provided":[130,176],"TIME.":[132],"is":[134,175],"lightweight,":[136],"plug-and-play":[137],"module":[138],"that":[139],"integrates":[140],"seamlessly":[141],"into":[142,152],"GCD":[144,155],"with":[146,168],"minimal":[147,169],"computational":[148,170],"overhead.":[149,171],"When":[150],"incorporated":[151],"one":[153],"prominent":[154],"method,":[156],"SimGCD,":[157],"achieves":[159],"up":[160],"15.4%":[162],"performance":[163],"improvement":[164],"over":[165],"baseline":[167],"The":[172],"implementation":[173],"code":[174],"https://github.com/Afleve/AFGCD.":[178]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}