{"id":"https://openalex.org/W4416137607","doi":"https://doi.org/10.1109/iccv51701.2025.01525","title":"DIMCIM: A Quantitative Evaluation Framework for Default-Mode Diversity and Generalization in Text-to-Image Generative Models","display_name":"DIMCIM: A Quantitative Evaluation Framework for Default-Mode Diversity and Generalization in Text-to-Image Generative Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416137607","doi":"https://doi.org/10.1109/iccv51701.2025.01525"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01525","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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.05108","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039475429","display_name":"Revant Teotia","orcid":"https://orcid.org/0000-0001-8835-7618"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Revant Teotia","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082026462","display_name":"Candace Ross","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Candace Ross","raw_affiliation_strings":["FAIR at Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR at Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058031547","display_name":"Karen Ullrich","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karen Ullrich","raw_affiliation_strings":["FAIR at Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR at Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078511139","display_name":"Sumit Chopra","orcid":"https://orcid.org/0009-0009-6637-2230"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sumit Chopra","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027811140","display_name":"Adriana Romero-Soriano","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adriana Romero-Soriano","raw_affiliation_strings":["FAIR at Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR at Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102935600","display_name":"Melissa Hall","orcid":"https://orcid.org/0009-0009-0509-1654"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Melissa Hall","raw_affiliation_strings":["FAIR at Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR at Meta","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029739727","display_name":"Matthew J. Muckley","orcid":"https://orcid.org/0000-0002-6525-8817"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthew Muckley","raw_affiliation_strings":["FAIR at Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR at Meta","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31077826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16431","last_page":"16440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.453000009059906,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.453000009059906,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.19689999520778656,"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/T10028","display_name":"Topic Modeling","score":0.04729999974370003,"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/generalization","display_name":"Generalization","score":0.7735000252723694},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.67330002784729},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6359999775886536},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.534600019454956},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.520799994468689},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48910000920295715},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4223000109195709},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42100000381469727}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7735000252723694},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7005000114440918},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.67330002784729},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6370000243186951},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6359999775886536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6230000257492065},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.534600019454956},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48910000920295715},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42100000381469727},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.41179999709129333},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4047999978065491},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.39250001311302185},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2549000084400177},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01525","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:2506.05108","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.05108","pdf_url":"https://arxiv.org/pdf/2506.05108","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":"doi:10.48550/arxiv.2506.05108","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.05108","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.05108","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.05108","pdf_url":"https://arxiv.org/pdf/2506.05108","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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416137607.pdf","grobid_xml":"https://content.openalex.org/works/W4416137607.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,116,174],"text-to-image":[3],"(T2I)":[4],"models":[5,114],"have":[6],"achieved":[7],"impressive":[8],"quality":[9],"and":[10,49,75,99,101,166,177,185,193],"consistency.":[11],"However,":[12],"this":[13,53],"has":[14],"come":[15],"at":[16,118],"the":[17,41,57,68,79,90,119,159],"cost":[18,120],"of":[19,43,64,121,162,170,200],"representation":[20],"diversity.":[21,179],"While":[22],"automatic":[23],"evaluation":[24],"methods":[25],"exist":[26],"for":[27,84,188],"benchmarking":[28],"model":[29,69,80,165,191,201],"diversity,":[30],"they":[31],"either":[32],"require":[33],"reference":[34],"image":[35],"datasets":[36],"or":[37],"lack":[38],"specificity":[39],"about":[40],"kind":[42],"diversity":[44,66,123,173,192],"measured,":[45],"limiting":[46],"their":[47],"adaptability":[48],"interpretability.":[50],"To":[51],"address":[52],"gap,":[54],"we":[55,110,154],"introduce":[56],"Does-it/Can-it":[58],"framework,":[59],"DIM-CIM,":[60],"a":[61,85,104,163,168,183,196],"reference-free":[62],"measurement":[63],"default-mode":[65,122,178],"(\"Does\"":[67],"generate":[70,81],"images":[71,176],"with":[72,96,143],"expected":[73],"attributes?)":[74],"generalization":[76,117],"capacity":[77],"(\"Can\"":[78],"diverse":[82],"attributes":[83,139],"particular":[86],"concept?).":[87],"We":[88],"construct":[89],"COCO-DIMCIM":[91],"benchmark,":[92],"which":[93],"is":[94],"seeded":[95],"COCO":[97],"concepts":[98],"captions":[100],"augmented":[102],"by":[103],"large":[105],"language":[106],"model.":[107],"With":[108],"COCO-DIMCIM,":[109],"find":[111],"that":[112,140],"widely-used":[113],"improve":[115],"when":[124,150],"scaling":[125],"from":[126],"1.5B":[127],"to":[128,157],"8.1B":[129],"parameters.":[130],"DIMCIM":[131,156],"also":[132],"identifies":[133],"fine-grained":[134],"failure":[135],"cases,":[136],"such":[137],"as":[138],"are":[141,147],"generated":[142,149],"generic":[144],"prompts":[145],"but":[146],"rarely":[148],"explicitly":[151],"requested.":[152],"Finally,":[153],"use":[155],"evaluate":[158],"training":[160,175],"data":[161],"T2I":[164,190],"observe":[167],"correlation":[169],"0.85":[171],"between":[172],"Our":[180],"work":[181],"provides":[182],"flexible":[184],"interpretable":[186],"framework":[187],"assessing":[189],"generalization,":[194],"enabling":[195],"more":[197],"comprehensive":[198],"understanding":[199],"performance.":[202]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}