{"id":"https://openalex.org/W3204392079","doi":null,"title":"ZSD-YOLO: Zero-Shot YOLO Detection using Vision-Language KnowledgeDistillation.","display_name":"ZSD-YOLO: Zero-Shot YOLO Detection using Vision-Language KnowledgeDistillation.","publication_year":2021,"publication_date":"2021-09-24","ids":{"openalex":"https://openalex.org/W3204392079","mag":"3204392079"},"language":"en","primary_location":{"id":"mag:3204392079","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2109.12066.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.12066.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032088645","display_name":"Johnathan Xie","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Johnathan Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042419001","display_name":"Shuai Zheng","orcid":"https://orcid.org/0000-0001-8560-8135","observed_orcids":["https://orcid.org/0000-0001-8560-8135"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai Zheng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-8560-8135","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8866999745368958,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.8866999745368958,"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":0.10320000350475311,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.007799999788403511,"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/zero-shot-object-detection","display_name":"zero-shot detection","score":0.949999988079071},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.8130000233650208},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8980000019073486},{"id":"https://openalex.org/keywords/clip","display_name":"CLIP","score":0.9240000247955322},{"id":"https://openalex.org/keywords/yolov5","display_name":"YOLOv5","score":0.996999979019165},{"id":"https://openalex.org/keywords/long-tailed-distributions","display_name":"long-tailed distributions","score":0.6639999747276306},{"id":"https://openalex.org/keywords/self-training","display_name":"self-training","score":0.9179999828338623},{"id":"https://openalex.org/keywords/coco","display_name":"COCO","score":0.7850000262260437}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.722034752368927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7094569206237793},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6623380780220032},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6213275194168091},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5966720581054688},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5761715173721313},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5627256631851196},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5162174701690674},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5136246085166931},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4882986545562744},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4416106939315796},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3338221311569214},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3204392079","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2109.12066.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3204392079","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2109.12066.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1483870316","https://openalex.org/W1676820704","https://openalex.org/W1846799578","https://openalex.org/W1861492603","https://openalex.org/W1993309459","https://openalex.org/W2031489346","https://openalex.org/W2041076459","https://openalex.org/W2081580037","https://openalex.org/W2098411764","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2134270519","https://openalex.org/W2138011018","https://openalex.org/W2168356304","https://openalex.org/W2570343428","https://openalex.org/W2789366140","https://openalex.org/W2791890924","https://openalex.org/W2796497263","https://openalex.org/W2806070179","https://openalex.org/W2905535961","https://openalex.org/W2948672349","https://openalex.org/W2952122856","https://openalex.org/W2963499153","https://openalex.org/W2971892976","https://openalex.org/W2997795356","https://openalex.org/W3034199269","https://openalex.org/W3092529717","https://openalex.org/W3093056553","https://openalex.org/W3106250896","https://openalex.org/W3135367836","https://openalex.org/W4320002812","https://openalex.org/W6893711219","https://openalex.org/W6922505924"],"related_works":["https://openalex.org/W4319779677","https://openalex.org/W3158124198","https://openalex.org/W4394593079","https://openalex.org/W7115588306","https://openalex.org/W2804761240","https://openalex.org/W7140293146","https://openalex.org/W4415800610","https://openalex.org/W3207088217","https://openalex.org/W4380558581","https://openalex.org/W2796497263"],"abstract_inverted_index":{"Real-world":[0],"object":[1,49,105,133],"sampling":[2],"produces":[3],"long-tailed":[4],"distributions":[5],"requiring":[6],"exponentially":[7],"more":[8],"images":[9,38,172],"for":[10],"rare":[11],"types.":[12],"Zero-shot":[13],"detection,":[14,62],"which":[15],"aims":[16],"to":[17,24,84,102,128],"detect":[18,129],"unseen":[19],"objects,":[20],"is":[21,33,55],"one":[22],"direction":[23],"address":[25],"this":[26,97],"problem.":[27],"A":[28],"dataset":[29],"such":[30,81],"as":[31,82],"COCO":[32,113],"extensively":[34],"annotated":[35],"across":[36,51,153],"many":[37],"but":[39],"with":[40,117],"a":[41,52,65,77,85,91,160,165],"sparse":[42],"number":[43,131],"of":[44,132,148],"categories":[45],"and":[46,57,73],"annotating":[47],"all":[48],"classes":[50,134],"diverse":[53],"domain":[54],"expensive":[56],"challenging.":[58],"To":[59],"advance":[60],"zero-shot":[61,78,114],"we":[63,99,158],"develop":[64,159],"Vision-Language":[66],"distillation":[67],"method":[68,150,162],"that":[69,107,141,163],"aligns":[70],"both":[71],"image":[72],"text":[74],"embeddings":[75],"from":[76,90],"pre-trained":[79],"model":[80,119,124],"CLIP":[83],"modified":[86],"semantic":[87],"prediction":[88],"head":[89],"one-stage":[92],"detector":[93,106],"like":[94],"YOLOv5.":[95],"With":[96],"method,":[98],"are":[100,151],"able":[101],"train":[103],"an":[104],"achieves":[108],"state-of-the-art":[109],"accuracy":[110],"on":[111],"the":[112,142,146],"detection":[115],"splits":[116],"fewer":[118],"parameters.":[120],"During":[121],"inference,":[122],"our":[123,149],"can":[125],"be":[126],"adapted":[127],"any":[130],"without":[135,169],"additional":[136],"training.":[137],"We":[138],"also":[139],"find":[140],"improvements":[143],"provided":[144],"by":[145],"scaling":[147],"consistent":[152],"various":[154],"YOLOv5":[155],"scales.":[156],"Furthermore,":[157],"self-training":[161],"provides":[164],"significant":[166],"score":[167],"improvement":[168],"needing":[170],"extra":[171],"nor":[173],"labels.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-10-11T00:00:00"}