{"id":"https://openalex.org/W4412536610","doi":"https://doi.org/10.1109/tpami.2025.3591018","title":"Sel4FT: Annotation Selection for Pretraining-Finetuning With Distribution Shift","display_name":"Sel4FT: Annotation Selection for Pretraining-Finetuning With Distribution Shift","publication_year":2025,"publication_date":"2025-07-21","ids":{"openalex":"https://openalex.org/W4412536610","doi":"https://doi.org/10.1109/tpami.2025.3591018","pmid":"https://pubmed.ncbi.nlm.nih.gov/40690348"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3591018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3591018","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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":"Han Lu","orcid":"https://orcid.org/0000-0002-1782-5127"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Lu","raw_affiliation_strings":["School of Computer Science and Engineering and MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","Department of Computer Science and Engineering and MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1782-5127","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering and MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering and MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yichen Xie","orcid":"https://orcid.org/0000-0003-4443-8795"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yichen Xie","raw_affiliation_strings":["University of California, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4443-8795","affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022382771","display_name":"Mingyu Ding","orcid":"https://orcid.org/0000-0001-6556-8359"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingyu Ding","raw_affiliation_strings":["University of California, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6556-8359","affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101770873","display_name":"Wei Zhan","orcid":"https://orcid.org/0000-0002-1474-1200"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Zhan","raw_affiliation_strings":["University of California, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1474-1200","affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019708391","display_name":"Xiaokang Yang","orcid":"https://orcid.org/0000-0003-4029-3322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokang Yang","raw_affiliation_strings":["School of Computer Science and Engineering and MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","Department of Computer Science and Engineering and MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4029-3322","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering and MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering and MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064077634","display_name":"Masayoshi Tomizuka","orcid":"https://orcid.org/0000-0003-0206-6639"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Masayoshi Tomizuka","raw_affiliation_strings":["University of California, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0206-6639","affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087158377","display_name":"Junchi Yan","orcid":"https://orcid.org/0000-0001-9639-7679"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junchi Yan","raw_affiliation_strings":["School of Computer Science and Engineering and MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","Department of Computer Science and Engineering and MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9639-7679","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering and MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering and MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5311,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.83585353,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"47","issue":"11","first_page":"9922","last_page":"9937"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.8435999751091003,"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/T11439","display_name":"Video Analysis and Summarization","score":0.8435999751091003,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.8054999709129333,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.7096999883651733,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/computer-science","display_name":"Computer science","score":0.6842188835144043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.607170820236206},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6066573262214661},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5941364765167236},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4079743027687073},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3823290467262268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6842188835144043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.607170820236206},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6066573262214661},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5941364765167236},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4079743027687073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3823290467262268}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3591018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3591018","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40690348","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40690348","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G187169856","display_name":null,"funder_award_id":"62222607","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1513874326","https://openalex.org/W2117539524","https://openalex.org/W2124244761","https://openalex.org/W2125101937","https://openalex.org/W2143668817","https://openalex.org/W2171235719","https://openalex.org/W2194775991","https://openalex.org/W2262342046","https://openalex.org/W2416374163","https://openalex.org/W2471138382","https://openalex.org/W2737258237","https://openalex.org/W2798820905","https://openalex.org/W2798991696","https://openalex.org/W2949736877","https://openalex.org/W2956371155","https://openalex.org/W2963015987","https://openalex.org/W2963696295","https://openalex.org/W2986514296","https://openalex.org/W2992308087","https://openalex.org/W2998508940","https://openalex.org/W3025091470","https://openalex.org/W3035524453","https://openalex.org/W3035682985","https://openalex.org/W3095809828","https://openalex.org/W3145450063","https://openalex.org/W3159481202","https://openalex.org/W3171007011","https://openalex.org/W3179550234","https://openalex.org/W3184557372","https://openalex.org/W3184966323","https://openalex.org/W3185341429","https://openalex.org/W3197097949","https://openalex.org/W3205626500","https://openalex.org/W3214423317","https://openalex.org/W4206648492","https://openalex.org/W4214705313","https://openalex.org/W4214893857","https://openalex.org/W4221145186","https://openalex.org/W4307823382","https://openalex.org/W4312252393","https://openalex.org/W4312312750","https://openalex.org/W4312677475","https://openalex.org/W4312775442","https://openalex.org/W4313156423","https://openalex.org/W4319300193","https://openalex.org/W4386065613","https://openalex.org/W4386071709","https://openalex.org/W4387490658","https://openalex.org/W4389104669","https://openalex.org/W4390872541","https://openalex.org/W4390872709","https://openalex.org/W4402715869"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W2033914206"],"abstract_inverted_index":{"The":[0],"pretraining-finetuning":[1],"paradigm":[2],"has":[3],"become":[4],"dominant":[5],"in":[6,49],"computer":[7],"vision,":[8],"yet":[9],"strategically":[10],"exploiting":[11],"limited":[12],"annotation":[13,41,102],"budgets":[14],"during":[15,104],"finetuning":[16],"remains":[17],"unexplored.":[18],"We":[19,36,79],"introduce":[20],"active":[21],"finetuning-a":[22],"novel":[23],"task":[24],"for":[25,110],"selecting":[26],"the":[27,58,85],"most":[28],"informative":[29],"samples":[30],"to":[31,53,131],"annotate":[32],"within":[33],"this":[34],"paradigm.":[35],"propose":[37],"Sel4FT,":[38],"a":[39,46,55],"unified":[40],"selection":[42,77],"framework":[43,97],"that":[44],"optimizes":[45],"parametric":[47],"model":[48],"continuous":[50],"feature":[51],"space":[52],"identify":[54],"subset":[56,91],"preserving":[57],"entire":[59],"pool's":[60],"distribution":[61,67],"while":[62],"maintaining":[63],"diversity.":[64],"To":[65],"address":[66],"shifts":[68],"from":[69],"data":[70,94],"augmentation,":[71],"we":[72],"develop":[73],"Sel4FT++":[74],"with":[75,126],"augmentation-aware":[76],"mechanisms.":[78],"theoretically":[80],"prove":[81],"our":[82],"approach":[83],"minimizes":[84],"Earth":[86],"Mover's":[87],"Distance":[88],"between":[89],"selected":[90],"and":[92,101,120],"full":[93],"pool.":[95],"Our":[96],"eliminates":[98],"iterative":[99],"retraining":[100],"process":[103],"selection,":[105],"providing":[106],"an":[107],"efficient":[108],"solution":[109],"real-world":[111],"deployment.":[112],"Extensive":[113],"experiments":[114],"on":[115],"image":[116],"classification,":[117],"long-tailed":[118],"recognition,":[119],"semantic":[121],"segmentation":[122],"demonstrate":[123],"state-of-the-art":[124],"performance":[125],"over":[127],"$100\\times$100\u00d7":[128],"speedup":[129],"compared":[130],"existing":[132],"methods.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-13T07:31:44.756512","created_date":"2025-10-10T00:00:00"}