{"id":"https://openalex.org/W4413145658","doi":"https://doi.org/10.1109/cvpr52734.2025.00858","title":"COUNTS: Benchmarking Object Detectors and Multimodal Large Language Models under Distribution Shifts","display_name":"COUNTS: Benchmarking Object Detectors and Multimodal Large Language Models under Distribution Shifts","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145658","doi":"https://doi.org/10.1109/cvpr52734.2025.00858"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5100631198","display_name":"Jiansheng Li","orcid":"https://orcid.org/0000-0002-3541-3927"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiansheng Li","raw_affiliation_strings":["Tsinghua University,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054379354","display_name":"Xingxuan Zhang","orcid":"https://orcid.org/0009-0002-4788-1127"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingxuan Zhang","raw_affiliation_strings":["Tsinghua University,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100613732","display_name":"Hao Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zou","raw_affiliation_strings":["Tsinghua University,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001311690","display_name":"Yige Guo","orcid":"https://orcid.org/0000-0003-2733-3801"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yige Guo","raw_affiliation_strings":["Tsinghua University,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061888153","display_name":"Renzhe Xu","orcid":"https://orcid.org/0000-0001-8418-0034"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renzhe Xu","raw_affiliation_strings":["Tsinghua University,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100638612","display_name":"Yilong Liu","orcid":"https://orcid.org/0000-0003-0398-1812"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilong Liu","raw_affiliation_strings":["Tsinghua University,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chuzhao Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuzhao Zhu","raw_affiliation_strings":["Tsinghua University,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101790419","display_name":"Yue He","orcid":"https://orcid.org/0000-0001-6776-4679"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue He","raw_affiliation_strings":["Tsinghua University,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009228005","display_name":"Peng Cui","orcid":"https://orcid.org/0000-0003-2957-8511"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Cui","raw_affiliation_strings":["Tsinghua University,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":3.346,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92575728,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"9186","last_page":"9198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9710999727249146,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9710999727249146,"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/benchmarking","display_name":"Benchmarking","score":0.821907639503479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7176258563995361},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.48545223474502563},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4753256142139435},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43285781145095825},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.4194389283657074},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41759130358695984},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08332088589668274},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07211211323738098}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.821907639503479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7176258563995361},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.48545223474502563},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4753256142139435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43285781145095825},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.4194389283657074},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41759130358695984},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08332088589668274},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07211211323738098},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335768","display_name":"National Postdoctoral Program for Innovative Talents","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W2112883198"],"abstract_inverted_index":{"Current":[0],"object":[1,22,60,113,175,208],"detectors":[2,23,114,176,209],"often":[3],"suffer":[4],"significant":[5,163],"performance":[6,158,216],"degradation":[7],"in":[8,139,159,170,201],"real-world":[9],"applications":[10],"when":[11],"encountering":[12],"distributional":[13,82,218],"shifts.":[14,219],"Consequently,":[15],"the":[16,52,108,127,133,184,202],"out-of-distribution":[17],"(OOD)":[18],"generalization":[19,54,110,135],"capability":[20],"of":[21,38,112,136,206,213],"has":[24],"garnered":[25],"increasing":[26],"attention":[27],"from":[28],"researchers.":[29],"Despite":[30],"this":[31,66],"growing":[32],"interest,":[33],"there":[34],"remains":[35],"a":[36,39,71],"lack":[37],"large-scale,":[40],"comprehensive":[41],"dataset":[42,74],"and":[43,62,87,122,152,165,177,187,192,204,210],"evaluation":[44],"benchmark":[45],"with":[46,75],"fine-grained":[47],"annotations":[48],"tailored":[49],"to":[50,105,131],"assess":[51,132],"OOD":[53,73,109,134,171],"on":[55,126],"more":[56,88],"intricate":[57],"tasks":[58],"like":[59],"detection":[61],"grounding.":[63],"To":[64],"address":[65],"gap,":[67],"we":[68,96],"introduce":[69,97],"COUNTS,":[70,95],"large-scale":[72],"object-level":[76],"annotations.":[77],"COUNTS":[78,198],"encompasses":[79],"14":[80],"natural":[81],"shifts,":[83],"over":[84],"222K":[85],"samples,":[86],"than":[89],"1,196K":[90],"labeled":[91],"bounding":[92],"boxes.":[93],"Leveraging":[94],"two":[98],"novel":[99],"benchmarks:":[100],"O(OD)1and":[101],"OODG.":[102],"O(OD)1is":[103],"designed":[104],"comprehensively":[106],"evaluate":[107],"capabilities":[111],"by":[115],"utilizing":[116],"controlled":[117],"distribution":[118],"shifts":[119],"between":[120],"training":[121],"testing":[123],"data.":[124],"OODG,":[125],"other":[128],"hand,":[129],"aims":[130],"grounding":[137,181],"abilities":[138],"multimodal":[140],"large":[141,150],"language":[142],"models":[143,151],"(MLLMs).":[144],"Our":[145],"findings":[146],"reveal":[147],"that,":[148],"while":[149],"extensive":[153],"pre-training":[154],"data":[155],"substantially":[156],"enhance":[157],"in-distribution":[160],"(IID)":[161],"scenarios,":[162],"limitations":[164],"opportunities":[166],"for":[167,173],"improvement":[168],"persist":[169],"contexts":[172],"both":[174],"MLLMs.":[178],"In":[179],"visual":[180],"tasks,":[182],"even":[183],"advanced":[185],"GPT-4o":[186],"Gemini-1.5":[188],"only":[189],"achieve":[190],"56.7%":[191],"28.0%":[193],"accuracy,":[194],"respectively.":[195],"We":[196],"hope":[197],"facilitates":[199],"advancements":[200],"development":[203],"assessment":[205],"robust":[207],"MLLMs":[211],"capable":[212],"maintaining":[214],"high":[215],"under":[217]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}