{"id":"https://openalex.org/W4403780684","doi":"https://doi.org/10.1145/3664647.3681213","title":"Towards Robustness Prompt Tuning with Fully Test-Time Adaptation for CLIP's Zero-Shot Generalization","display_name":"Towards Robustness Prompt Tuning with Fully Test-Time Adaptation for CLIP's Zero-Shot Generalization","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780684","doi":"https://doi.org/10.1145/3664647.3681213"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681213","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681213","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664647.3681213","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101985101","display_name":"Ran Wang","orcid":"https://orcid.org/0009-0004-8397-3410"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Ran Wang","raw_affiliation_strings":["Australian Artificial Intelligence Institute, FEIT, University of Technology Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0009-0004-8397-3410","affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute, FEIT, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071218354","display_name":"Hua Zuo","orcid":"https://orcid.org/0000-0002-9122-0775"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hua Zuo","raw_affiliation_strings":["Australian Artificial Intelligence Institute, FEIT, University of Technology Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9122-0775","affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute, FEIT, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087852871","display_name":"Zhen Fang","orcid":"https://orcid.org/0000-0003-0602-6255"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhen Fang","raw_affiliation_strings":["Australian Artificial Intelligence Institute, FEIT, University of Technology Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0602-6255","affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute, FEIT, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100675577","display_name":"Jie L\u00fc","orcid":"https://orcid.org/0000-0003-0690-4732"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jie Lu","raw_affiliation_strings":["Australian Artificial Intelligence Institute, FEIT, University of Technology Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0690-4732","affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute, FEIT, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101985101"],"corresponding_institution_ids":["https://openalex.org/I114017466"],"apc_list":null,"apc_paid":null,"fwci":1.571,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84207183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8604","last_page":"8612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9835000038146973,"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":0.9815000295639038,"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/robustness","display_name":"Robustness (evolution)","score":0.7891597747802734},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6116379499435425},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5651646852493286},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4832116365432739},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4324362277984619},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3533719778060913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3517906665802002},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3433535695075989},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2836500108242035},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08072492480278015},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.07808372378349304},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.05910578370094299}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7891597747802734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6116379499435425},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5651646852493286},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4832116365432739},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4324362277984619},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3533719778060913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3517906665802002},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3433535695075989},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2836500108242035},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08072492480278015},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.07808372378349304},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.05910578370094299},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681213","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681213","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3664647.3681213","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681213","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W2108598243","https://openalex.org/W2138011018","https://openalex.org/W2166049352","https://openalex.org/W2533598788","https://openalex.org/W2896457183","https://openalex.org/W2964194231","https://openalex.org/W3025988480","https://openalex.org/W3037492894","https://openalex.org/W3164101295","https://openalex.org/W3198377975","https://openalex.org/W3210129272","https://openalex.org/W4285345750","https://openalex.org/W4285787895","https://openalex.org/W4300362655","https://openalex.org/W4309956828","https://openalex.org/W4386065763","https://openalex.org/W4392172801","https://openalex.org/W4393160557","https://openalex.org/W4394862984","https://openalex.org/W6600558321","https://openalex.org/W6829576860"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W2997567050","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2080152487","https://openalex.org/W3083152911","https://openalex.org/W3022347918"],"abstract_inverted_index":{"In":[0,233],"the":[1,7,46,81,131,171,192],"field":[2],"of":[3],"Vision-Language":[4],"Models":[5],"(VLM),":[6],"Contrastive":[8],"Language-Image":[9],"Pretraining":[10],"(CLIP)":[11],"model":[12,83],"has":[13],"yielded":[14],"outstanding":[15],"performance":[16,246],"on":[17,35,111],"many":[18,73],"downstream":[19],"tasks":[20],"through":[21,86],"prompt":[22,184],"tuning.":[23],"By":[24],"integrating":[25],"image":[26,99],"and":[27,42,139,247],"text":[28,48],"representations,":[29],"CLIP":[30,51,82],"exhibits":[31],"zero-shot":[32,66,160,220,237],"generalization":[33,67,221,238],"capabilities":[34],"unseen":[36,57],"data.":[37],"However,":[38],"when":[39],"new":[40],"categories":[41],"distribution":[43,175],"shifts":[44],"occur,":[45],"pretrained":[47],"embeddings":[49],"in":[50,64,130,245],"may":[52],"not":[53,213],"align":[54],"well":[55],"with":[56,152],"images,":[58],"potentially":[59],"leading":[60],"to":[61,79,103,157,169,186],"a":[62,87,127,147,182,197,206],"decrease":[63],"CLIP's":[65,159,219],"performance.":[68],"To":[69,134],"address":[70],"this":[71],"issue,":[72],"existing":[74,242],"methods":[75,109,120,244],"use":[76],"test":[77,223],"samples":[78],"update":[80],"during":[84],"testing":[85,132],"process":[88],"known":[89],"as":[90,98,196],"Test-Time":[91],"Adaptation":[92],"(TTA).":[93],"Previous":[94],"TTA":[95],"techniques,":[96],"such":[97],"augmentation,":[100],"can":[101,114],"lead":[102],"overfitting":[104],"given":[105],"outlying":[106,143],"samples,":[107,144],"while":[108],"based":[110],"teacher-student":[112],"distillation":[113],"increase":[115,122],"memory":[116,228],"use.":[117],"Further,":[118],"these":[119],"significantly":[121,248],"inference":[123,231,250],"time,":[124],"which":[125],"is":[126,205],"crucial":[128],"factor":[129],"phase.":[133],"improve":[135],"robustness,":[136],"mitigate":[137],"overfitting,":[138],"reduce":[140],"bias":[141],"toward":[142,174],"we":[145],"propose":[146],"novel":[148],"method:":[149],"Self-Text":[150],"Distillation":[151],"Conjugate":[153],"Pseudo-labels":[154],"(SCP),":[155],"designed":[156],"enhance":[158,170],"generalization.":[161],"SCP":[162,204,240],"uses":[163],"gradient":[164],"information":[165],"from":[166,190],"conjugate":[167],"pseudo-labels":[168],"model's":[172],"robustness":[173],"shifts.":[176],"It":[177,216],"also":[178],"innovates":[179],"by":[180],"using":[181],"fixed":[183],"list":[185],"distil":[187],"learnable":[188],"prompts":[189],"within":[191],"same":[193],"model,":[194],"acting":[195],"self-regulation":[198],"mechanism":[199],"that":[200,211],"minimizes":[201],"overfitting.":[202],"Additionally,":[203],"fully":[207],"test-time":[208],"adaptation":[209],"method":[210],"does":[212],"require":[214],"retraining.":[215],"directly":[217],"improves":[218],"at":[222],"time":[224],"without":[225],"increasing":[226],"either":[227],"overheads":[229],"or":[230],"time.":[232,251],"evaluations":[234],"across":[235],"three":[236],"scenarios,":[239],"surpasses":[241],"state-of-the-art":[243],"reduces":[249]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}