{"id":"https://openalex.org/W4415345610","doi":"https://doi.org/10.1109/iccv51701.2025.00108","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","display_name":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415345610","doi":"https://doi.org/10.1109/iccv51701.2025.00108"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00108","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/2507.04051","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100723981","display_name":"Xiao Liu","orcid":"https://orcid.org/0009-0007-4780-8399"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiao Liu","raw_affiliation_strings":["Hefei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049953967","display_name":"Nan Pu","orcid":"https://orcid.org/0000-0002-2179-8301"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nan Pu","raw_affiliation_strings":["University of Trento"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trento","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100305563","display_name":"Haiyang Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Haiyang Zheng","raw_affiliation_strings":["University of Trento"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trento","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010490908","display_name":"Wenjing Li","orcid":"https://orcid.org/0000-0003-3201-6675"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjing Li","raw_affiliation_strings":["Hefei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027171279","display_name":"Nicu Sebe","orcid":"https://orcid.org/0000-0002-6597-7248"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicu Sebe","raw_affiliation_strings":["University of Trento"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trento","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101193877","display_name":"Zhun Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhun Zhong","raw_affiliation_strings":["Hefei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100723981"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41312294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1078","last_page":"1087"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9442999958992004,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.9442999958992004,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/leverage","display_name":"Leverage (statistics)","score":0.6319000124931335},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6092000007629395},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5098000168800354},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.48069998621940613},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.4731000065803528},{"id":"https://openalex.org/keywords/transferability","display_name":"Transferability","score":0.4584999978542328},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44600000977516174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7217000126838684},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6319000124931335},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6092000007629395},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5098000168800354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4916999936103821},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.48069998621940613},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.4731000065803528},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.4584999978542328},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43799999356269836},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3165000081062317},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26010000705718994},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iccv51701.2025.00108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00108","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:2507.04051","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.04051","pdf_url":"https://arxiv.org/pdf/2507.04051","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"},{"id":"pmh:oai:zenodo.org:19109974","is_oa":true,"landing_page_url":"https://arxiv.org/abs/arXiv:2507.04051v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference of Computer Vision","raw_type":"info:eu-repo/semantics/conferencePaper"},{"id":"pmh:oai:iris.unitn.it:11572/486951","is_oa":false,"landing_page_url":"https://hdl.handle.net/11572/486951","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.04051","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.04051","pdf_url":"https://arxiv.org/pdf/2507.04051","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/G1157864687","display_name":null,"funder_award_id":"JZ2025HGTB0219","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2896194320","display_name":null,"funder_award_id":"62402157","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G330524316","display_name":null,"funder_award_id":"101120237","funder_id":"https://openalex.org/F7311471023","funder_display_name":"NextGenerationEU"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F7311471023","display_name":"NextGenerationEU","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"<p>In":[0],"this":[1,88],"paper,":[2],"we":[3,90,109,130,152],"investigate":[4],"a":[5,92,105,132,154],"practical":[6],"yet":[7],"challenging":[8],"task:":[9],"On-the-fly":[10],"Category":[11],"Discovery":[12],"(OCD).":[13],"This":[14],"task":[15],"focuses":[16],"on":[17,117,198],"the":[18,36,58,67,121,138,168,174,183,190],"online":[19],"identification":[20],"of":[21,176,192],"newly":[22],"arriving":[23],"stream":[24],"data":[25,166],"that":[26,141],"may":[27],"belong":[28],"to":[29,48,125,136,158],"both":[30,177],"known":[31,71,144,178],"and":[32,102,179],"unknown":[33,180],"categories,":[34],"utilizing":[35],"category":[37,161],"knowledge":[38,52,68,162],"from":[39,53,143],"only":[40,54],"labeled":[41,55],"data.":[42,56],"Existing":[43],"OCD":[44,94,148,169],"methods":[45,63,197],"are":[46,81],"devoted":[47],"fully":[49],"mining":[50],"transferable":[51],"However,":[57],"transferability":[59],"learned":[60],"by":[61],"these":[62],"is":[64,73],"limited":[65],"because":[66],"contained":[69,163],"in":[70,83,104,120,164],"categories":[72,145,181],"often":[74],"insufficient,":[75],"especially":[76],"when":[77],"few":[78],"annotated":[79],"data/categories":[80],"available":[82],"fine-grained":[84,200],"recognition.":[85],"To":[86],"mitigate":[87],"limitation,":[89],"propose":[91,131],"diffusion-based":[93],"framework,":[95],"dubbed":[96],"DiffGRE,":[97],"which":[98,171],"integrates":[99],"Generation,":[100],"Refinement,":[101],"Encoding":[103],"multi-stage":[106],"fashion.":[107],"Specifically,":[108],"first":[110],"design":[111],"an":[112],"attribute-composition":[113],"generation":[114],"method":[115],"based":[116],"cross-image":[118],"interpolation":[119],"diffusion":[122],"latent":[123],"space":[124],"synthesize":[126],"novel":[127],"samples.":[128],"Then,":[129],"diversity-driven":[133],"refinement":[134],"approach":[135],"select":[137],"synthesized":[139,165],"images":[140],"differ":[142],"for":[146],"subsequent":[147],"model":[149],"training.":[150],"Finally,":[151],"leverage":[153],"semi-supervised":[155],"leader":[156],"encoding":[157],"inject":[159],"additional":[160],"into":[167],"models,":[170],"can":[172],"benefit":[173],"discovery":[175],"during":[182],"on-the-fly":[184],"inference":[185],"process.":[186],"Extensive":[187],"experiments":[188],"demonstrate":[189],"superiority":[191],"our":[193],"DiffGRE":[194],"over":[195],"previous":[196],"six":[199],"datasets.</p>":[201]},"counts_by_year":[],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2025-10-20T00:00:00"}