{"id":"https://openalex.org/W3206477178","doi":"https://doi.org/10.18653/v1/2022.findings-acl.118","title":"Semantically Distributed Robust Optimization for Vision-and-Language Inference","display_name":"Semantically Distributed Robust Optimization for Vision-and-Language Inference","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3206477178","doi":"https://doi.org/10.18653/v1/2022.findings-acl.118","mag":"3206477178"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.findings-acl.118","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.findings-acl.118","pdf_url":"https://aclanthology.org/2022.findings-acl.118.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.findings-acl.118.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035343276","display_name":"Tejas Gokhale","orcid":"https://orcid.org/0000-0002-5593-2804"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tejas Gokhale","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090079170","display_name":"Abhishek Chaudhary","orcid":"https://orcid.org/0000-0002-6602-7279"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek Chaudhary","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017986865","display_name":"Pratyay Banerjee","orcid":"https://orcid.org/0000-0001-5634-410X"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pratyay Banerjee","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083735830","display_name":"Chitta Baral","orcid":"https://orcid.org/0000-0002-7549-723X"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chitta Baral","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002278578","display_name":"Yezhou Yang","orcid":"https://orcid.org/0000-0003-0126-8976"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yezhou Yang","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":1.1965,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86399824,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1493","last_page":"1513"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.998199999332428,"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/T10028","display_name":"Topic Modeling","score":0.9890999794006348,"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/computer-science","display_name":"Computer science","score":0.7955517768859863},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6697711944580078},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6693116426467896},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.6162010431289673},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5976287722587585},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5807278156280518},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5657997131347656},{"id":"https://openalex.org/keywords/multilinear-map","display_name":"Multilinear map","score":0.5419477224349976},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42166951298713684},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4141905903816223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7955517768859863},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6697711944580078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6693116426467896},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6162010431289673},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5976287722587585},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5807278156280518},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5657997131347656},{"id":"https://openalex.org/C84392682","wikidata":"https://www.wikidata.org/wiki/Q1952404","display_name":"Multilinear map","level":2,"score":0.5419477224349976},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42166951298713684},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4141905903816223},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2022.findings-acl.118","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.findings-acl.118","pdf_url":"https://aclanthology.org/2022.findings-acl.118.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2022","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.findings-acl.118","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.findings-acl.118","pdf_url":"https://aclanthology.org/2022.findings-acl.118.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2022","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G160522031","display_name":null,"funder_award_id":"FA8750-19-C-0003","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G2264743483","display_name":"RI: Small: A Cognitive Framework for Technical, Hard and Explainable Question Answering (THE-QA) with respect to Combined Textual and Visual Inputs","funder_award_id":"1816039","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5868586035","display_name":"CAREER: Visual Recognition with Knowledge","funder_award_id":"1750082","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8856878232","display_name":"RI: Small: SM-An Active Approach for Data Engineering to Improve Vision-Language Tasks","funder_award_id":"2132724","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G915575692","display_name":null,"funder_award_id":"W911NF-20-2-0006","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3206477178.pdf","grobid_xml":"https://content.openalex.org/works/W3206477178.grobid-xml"},"referenced_works_count":84,"referenced_works":["https://openalex.org/W147998453","https://openalex.org/W639708223","https://openalex.org/W1577980105","https://openalex.org/W1840435438","https://openalex.org/W1965555277","https://openalex.org/W2098824882","https://openalex.org/W2112980792","https://openalex.org/W2155195660","https://openalex.org/W2187089797","https://openalex.org/W2250539671","https://openalex.org/W2254249950","https://openalex.org/W2293768274","https://openalex.org/W2560730294","https://openalex.org/W2561715562","https://openalex.org/W2608109911","https://openalex.org/W2613718673","https://openalex.org/W2767075075","https://openalex.org/W2788496822","https://openalex.org/W2789524546","https://openalex.org/W2798665661","https://openalex.org/W2798667726","https://openalex.org/W2799007037","https://openalex.org/W2806187986","https://openalex.org/W2810689564","https://openalex.org/W2891308403","https://openalex.org/W2933138175","https://openalex.org/W2947415936","https://openalex.org/W2949128310","https://openalex.org/W2951174316","https://openalex.org/W2951286828","https://openalex.org/W2953039212","https://openalex.org/W2962718684","https://openalex.org/W2962935454","https://openalex.org/W2963060032","https://openalex.org/W2963126845","https://openalex.org/W2963341956","https://openalex.org/W2963394326","https://openalex.org/W2963403868","https://openalex.org/W2963530300","https://openalex.org/W2963565751","https://openalex.org/W2963644680","https://openalex.org/W2963846996","https://openalex.org/W2963969878","https://openalex.org/W2964116600","https://openalex.org/W2964212410","https://openalex.org/W2964253222","https://openalex.org/W2966715458","https://openalex.org/W2970078867","https://openalex.org/W2970231061","https://openalex.org/W2970608575","https://openalex.org/W2971145119","https://openalex.org/W2971296908","https://openalex.org/W2981851019","https://openalex.org/W2988217457","https://openalex.org/W2991497298","https://openalex.org/W3004346089","https://openalex.org/W3006647218","https://openalex.org/W3007685714","https://openalex.org/W3034188691","https://openalex.org/W3034995113","https://openalex.org/W3035507081","https://openalex.org/W3035512383","https://openalex.org/W3035517717","https://openalex.org/W3043057662","https://openalex.org/W3082274269","https://openalex.org/W3089631405","https://openalex.org/W3090449556","https://openalex.org/W3102995547","https://openalex.org/W3104788521","https://openalex.org/W3105232955","https://openalex.org/W3105604018","https://openalex.org/W3105881229","https://openalex.org/W3106544837","https://openalex.org/W3110388292","https://openalex.org/W3169948074","https://openalex.org/W3171312896","https://openalex.org/W3171774521","https://openalex.org/W3173464813","https://openalex.org/W3176134838","https://openalex.org/W4288089799","https://openalex.org/W4293846201","https://openalex.org/W4299356147","https://openalex.org/W4300996741","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W1999178348","https://openalex.org/W4296311369","https://openalex.org/W4318719034","https://openalex.org/W37958683","https://openalex.org/W2396820687","https://openalex.org/W410723623","https://openalex.org/W2413243053","https://openalex.org/W3035010459","https://openalex.org/W4379251913"],"abstract_inverted_index":{"Analysis":[0],"of":[1,111],"vision-and-language":[2],"models":[3],"has":[4],"revealed":[5],"their":[6],"brittleness":[7],"under":[8],"linguistic":[9,63],"phenomena":[10],"such":[11],"as":[12,97,99],"paraphrasing,":[13],"negation,":[14],"textual":[15],"entailment,":[16],"and":[17,91],"word":[18],"substitutions":[19],"with":[20,72,86],"synonyms":[21],"or":[22],"antonyms.":[23],"While":[24],"data":[25],"augmentation":[26],"techniques":[27],"have":[28],"been":[29],"designed":[30],"to":[31,76,101,114],"mitigate":[32],"against":[33],"these":[34,78],"failure":[35],"modes,":[36],"methods":[37],"that":[38,59],"can":[39],"integrate":[40],"this":[41,50,112],"knowledge":[42],"into":[43],"the":[44,109],"training":[45],"pipeline":[46],"remain":[47],"under-explored.":[48],"In":[49],"paper,":[51],"we":[52],"present":[53],"SDRO":[54],",":[55],"a":[56,61,66],"model-agnostic":[57],"method":[58,113],"utilizes":[60],"set":[62],"transformations":[64,79],"in":[65],"distributed":[67],"robust":[68],"optimization":[69],"setting,":[70],"along":[71],"an":[73],"ensembling":[74],"technique":[75],"leverage":[77],"during":[80],"inference.":[81],"Experiments":[82,104],"on":[83,105],"benchmark":[84],"datasets":[85],"images":[87],"(NLVR":[88],"2":[89],")":[90],"video":[92],"(VIOLIN)":[93],"demonstrate":[94],"performance":[95],"improvements":[96],"well":[98],"robustness":[100],"adversarial":[102],"attacks.":[103],"binary":[106],"VQA":[107],"explore":[108],"generalizability":[110],"other":[115],"V&L":[116],"tasks.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}