{"id":"https://openalex.org/W4416213881","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229323","title":"Intriguing Differences Between Zero-Shot and Systematic Evaluations of Vision-Language Transformer Models","display_name":"Intriguing Differences Between Zero-Shot and Systematic Evaluations of Vision-Language Transformer Models","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416213881","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229323"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","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/A5028569628","display_name":"Shaeke Salman","orcid":null},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shaeke Salman","raw_affiliation_strings":["Florida State University,Department of Computer Science,Tallahassee,Florida"],"affiliations":[{"raw_affiliation_string":"Florida State University,Department of Computer Science,Tallahassee,Florida","institution_ids":["https://openalex.org/I103163165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025739268","display_name":"Montasir Shams","orcid":null},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Montasir Shams","raw_affiliation_strings":["Florida State University,Department of Computer Science,Tallahassee,Florida"],"affiliations":[{"raw_affiliation_string":"Florida State University,Department of Computer Science,Tallahassee,Florida","institution_ids":["https://openalex.org/I103163165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102867647","display_name":"Xiuwen Liu","orcid":"https://orcid.org/0000-0002-9320-3872"},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiuwen Liu","raw_affiliation_strings":["Florida State University,Department of Computer Science,Tallahassee,Florida"],"affiliations":[{"raw_affiliation_string":"Florida State University,Department of Computer Science,Tallahassee,Florida","institution_ids":["https://openalex.org/I103163165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103238499","display_name":"Lingjiong Zhu","orcid":"https://orcid.org/0000-0001-7595-160X"},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lingjiong Zhu","raw_affiliation_strings":["Florida State University,Department of Mathematics,Tallahassee,Florida"],"affiliations":[{"raw_affiliation_string":"Florida State University,Department of Mathematics,Tallahassee,Florida","institution_ids":["https://openalex.org/I103163165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028569628"],"corresponding_institution_ids":["https://openalex.org/I103163165"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36981835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3310999870300293,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3310999870300293,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.2467000037431717,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0649000033736229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6553999781608582},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.51419997215271},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41839998960494995},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4180999994277954},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.39989998936653137},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.3278999924659729}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6553999781608582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6294000148773193},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.51419997215271},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4180999994277954},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.39989998936653137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3995000123977661},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3723999857902527},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2793999910354614},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C100253034","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Systematic error","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2566079294","https://openalex.org/W2952984539","https://openalex.org/W2972324944","https://openalex.org/W3145185940","https://openalex.org/W3205945722","https://openalex.org/W4225796928","https://openalex.org/W4231449374","https://openalex.org/W4288083516","https://openalex.org/W4298001211","https://openalex.org/W4376226279","https://openalex.org/W4379539462","https://openalex.org/W4386071707","https://openalex.org/W4393157467","https://openalex.org/W4405785743"],"related_works":[],"abstract_inverted_index":{"Transformer-based":[0],"models":[1,26,62,151],"have":[2,132],"dominated":[3],"natural":[4],"language":[5],"processing":[6],"and":[7,34,64],"other":[8,149],"areas":[9],"in":[10],"the":[11,46,49,88,98,105,128,163],"last":[12],"few":[13],"years":[14],"due":[15,30],"to":[16,31,42,66,86,126,141,148,161],"their":[17,32],"superior":[18],"(zero-shot)":[19],"performance":[20],"on":[21,75],"benchmark":[22],"datasets.":[23,70],"However,":[24],"these":[25],"are":[27,39,52,84,146],"poorly":[28],"understood":[29],"complexity":[33],"size.":[35],"While":[36],"probing-based":[37],"methods":[38],"widely":[40],"used":[41,94],"understand":[43],"specific":[44],"properties,":[45],"structures":[47],"of":[48,91],"representation":[50],"space":[51,90],"not":[53],"systematically":[54],"characterized;":[55],"consequently,":[56],"it":[57,113],"is":[58],"unclear":[59],"how":[60],"such":[61],"generalize":[63],"overgeneralize":[65],"new":[67],"inputs":[68],"beyond":[69],"In":[71],"this":[72],"paper,":[73],"based":[74],"our":[76,144],"recently":[77],"proposed":[78],"gradient":[79],"descent":[80],"optimization":[81],"method,":[82],"we":[83,101,122],"able":[85],"explore":[87],"embedding":[89],"a":[92,119,124,138,158],"commonly":[93],"vision-language":[95],"model.":[96],"Using":[97,118],"Imagenette":[99],"dataset,":[100],"show":[102],"that":[103,143],"while":[104],"model":[106,140],"achieves":[107],"over":[108],"99%":[109],"zero-shot":[110],"classification":[111],"performance,":[112],"fails":[114],"systematic":[115],"evaluations":[116],"completely.":[117],"linear":[120],"approximation,":[121],"provide":[123],"framework":[125],"explain":[127],"striking":[129],"differences.":[130],"We":[131,155],"also":[133,156],"obtained":[134],"similar":[135],"results":[136,145],"using":[137],"different":[139],"support":[142],"applicable":[147],"transformer":[150],"with":[152],"continuous":[153],"inputs.":[154],"propose":[157],"robust":[159],"way":[160],"detect":[162],"modified":[164],"images.":[165]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}