{"id":"https://openalex.org/W4403364591","doi":"https://doi.org/10.48550/arxiv.2410.07648","title":"FLIER: Few-shot Language Image Models Embedded with Latent Representations","display_name":"FLIER: Few-shot Language Image Models Embedded with Latent Representations","publication_year":2024,"publication_date":"2024-10-10","ids":{"openalex":"https://openalex.org/W4403364591","doi":"https://doi.org/10.48550/arxiv.2410.07648"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.07648","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.07648","pdf_url":"https://arxiv.org/pdf/2410.07648","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":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.07648","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007413026","display_name":"Zhinuo Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Zhinuo","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101578809","display_name":"Peng Zhou","orcid":"https://orcid.org/0000-0003-3736-1611","observed_orcids":["https://orcid.org/0000-0003-3736-1611"]},"institutions":[{"id":"https://openalex.org/I211433327","display_name":"Ministry of Natural Resources","ror":"https://ror.org/02kxqx159","country_code":"CN","type":"government","lineage":["https://openalex.org/I211433327","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I4210109544","display_name":"Second Institute of Oceanography","ror":"https://ror.org/01tkb7c15","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210109544"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Peng","raw_affiliation_strings":["Second Institute of Oceanography , Ministry of Natural Resources"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Second Institute of Oceanography , Ministry of Natural Resources","institution_ids":["https://openalex.org/I211433327","https://openalex.org/I4210109544"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091365447","display_name":"Xiaoyong Pan","orcid":"https://orcid.org/0000-0001-5010-464X","observed_orcids":["https://orcid.org/0000-0001-5010-464X"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan, Xiaoyong","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.635699987411499,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.635699987411499,"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":0.36059999465942383,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0012000000569969416,"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/few-shot-learning","display_name":"few-shot learning","score":0.7839999794960022},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8989999890327454},{"id":"https://openalex.org/keywords/latent-representations","display_name":"latent representations","score":0.796999990940094},{"id":"https://openalex.org/keywords/clip","display_name":"CLIP","score":0.7639999985694885},{"id":"https://openalex.org/keywords/latent-diffusion-models","display_name":"latent diffusion models","score":0.9039999842643738},{"id":"https://openalex.org/keywords/stable-diffusion","display_name":"Stable Diffusion","score":0.953000009059906},{"id":"https://openalex.org/keywords/u-net","display_name":"U-Net","score":0.5889999866485596},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.6579999923706055},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.5649999976158142},{"id":"https://openalex.org/keywords/prompt-learning","display_name":"prompt learning","score":0.3970000147819519},{"id":"https://openalex.org/keywords/visual-recognition","display_name":"visual recognition","score":0.30399999022483826}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7536721229553223},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5907485485076904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5430324673652649},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4170720875263214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38139551877975464},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3364472985267639},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07073169946670532},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.05962657928466797},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2410.07648","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.07648","pdf_url":"https://arxiv.org/pdf/2410.07648","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.07648","doi":"https://doi.org/10.48550/arxiv.2410.07648","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.07648","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.07648","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.07648","pdf_url":"https://arxiv.org/pdf/2410.07648","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":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403364591.pdf","grobid_xml":"https://content.openalex.org/works/W4403364591.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W3204019825"],"abstract_inverted_index":{"As":[0],"the":[1,69,77,87,96,151,169,193],"boosting":[2],"development":[3],"of":[4,34,63,104,148],"large":[5],"vision-language":[6,146,203],"models":[7,51],"like":[8],"Contrastive":[9],"Language-Image":[10],"Pre-training":[11],"(CLIP),":[12],"many":[13],"CLIP-like":[14],"methods":[15,36],"have":[16,30,53],"shown":[17,54],"impressive":[18],"abilities":[19],"on":[20,43,57,227,237],"visual":[21,229],"recognition,":[22],"especially":[23],"in":[24,79,106,202],"low-data":[25],"regimes":[26],"scenes.":[27],"However,":[28],"we":[29,90,117,180],"noticed":[31],"that":[32,81,233],"most":[33,200,241],"these":[35],"are":[37,99,111],"limited":[38],"to":[39,191,218],"introducing":[40,133],"new":[41],"modifications":[42],"text":[44],"and":[45,101,150,161,223],"image":[46,58,130,141,213],"encoder.":[47],"Recently,":[48],"latent":[49,70,97,126,135,152,163,175,194,206],"diffusion":[50],"(LDMs)":[52],"good":[55],"ability":[56],"generation.":[59],"The":[60,205],"potent":[61],"capabilities":[62],"LDMs":[64],"direct":[65],"our":[66],"focus":[67],"towards":[68],"representations":[71,98,153,164,176],"sampled":[72],"by":[73,76,132],"UNet.":[74],"Inspired":[75],"conjecture":[78],"CoOp":[80],"learned":[82],"prompts":[83],"encode":[84],"meanings":[85],"beyond":[86],"existing":[88],"vocabulary,":[89],"assume":[91],"that,":[92],"for":[93,129,240],"deep":[94],"models,":[95],"concise":[100],"accurate":[102],"understanding":[103],"images,":[105],"which":[107,196],"high-frequency,":[108],"imperceptible":[109],"details":[110],"abstracted":[112],"away.":[113],"In":[114],"this":[115],"paper,":[116],"propose":[118],"a":[119,134,182],"Few-shot":[120],"Language":[121],"Image":[122],"model":[123],"Embedded":[124],"with":[125,139,168,187,211],"Representations":[127],"(FLIER)":[128],"recognition":[131],"encoder":[136,207],"jointly":[137,209],"trained":[138,210],"CLIP's":[140,212],"encoder,":[142,195,214],"it":[143],"incorporates":[144],"pre-trained":[145,216],"knowledge":[147,217],"CLIP":[149],"from":[154,172],"Stable":[155,166],"Diffusion.":[156],"We":[157],"first":[158],"generate":[159],"images":[160],"corresponding":[162],"via":[165],"Diffusion":[167],"textual":[170],"inputs":[171],"GPT-3.":[173],"With":[174],"as":[177],"\"models-understandable":[178],"pixels\",":[179],"introduce":[181],"flexible":[183],"convolutional":[184,189],"neural":[185],"network":[186],"two":[188],"layers":[190],"be":[192],"is":[197,208],"simpler":[198],"than":[199],"encoders":[201],"models.":[204],"transferring":[215],"downstream":[219],"tasks":[220,231],"better.":[221],"Experiments":[222],"extensive":[224],"ablation":[225],"studies":[226],"various":[228],"classification":[230],"demonstrate":[232],"FLIER":[234],"performs":[235],"state-of-the-art":[236],"11":[238],"datasets":[239],"few-shot":[242],"classification.":[243]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2024-10-13T00:00:00"}