{"id":"https://openalex.org/W4410356879","doi":"https://doi.org/10.1145/3672608.3707739","title":"Supervised Contrastive Learning with Importance-based CutOut for Few-shot Image Classification","display_name":"Supervised Contrastive Learning with Importance-based CutOut for Few-shot Image Classification","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4410356879","doi":"https://doi.org/10.1145/3672608.3707739"},"language":"en","primary_location":{"id":"doi:10.1145/3672608.3707739","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3672608.3707739","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3672608.3707739","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 40th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3672608.3707739","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Seokhee Jo","orcid":"https://orcid.org/0000-0002-8539-6125"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seokhee Jo","raw_affiliation_strings":["Artificial Intelligence Research Center, JLK Inc., Seoul, Republic of Korea","Sogang University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-8539-6125","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center, JLK Inc., Seoul, Republic of Korea","institution_ids":[]},{"raw_affiliation_string":"Sogang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022288678","display_name":"Jungmin So","orcid":"https://orcid.org/0000-0001-5486-9068"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jungmin So","raw_affiliation_strings":["Sogang University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-5486-9068","affiliations":[{"raw_affiliation_string":"Sogang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I148751991"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148751991"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06392491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1065","last_page":"1073"},"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":0.9994000196456909,"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":0.9994000196456909,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9941999912261963,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.715949296951294},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6974374651908875},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.6342906951904297},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5668824911117554},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47884559631347656},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4627620577812195},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42688918113708496},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3792165219783783},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.05406346917152405}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.715949296951294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6974374651908875},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.6342906951904297},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5668824911117554},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47884559631347656},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4627620577812195},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42688918113708496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3792165219783783},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.05406346917152405},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3672608.3707739","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3672608.3707739","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3672608.3707739","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 40th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3672608.3707739","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3672608.3707739","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3672608.3707739","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 40th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7232038512","display_name":null,"funder_award_id":"2021S1A5A2A03064795","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410356879.pdf","grobid_xml":"https://content.openalex.org/works/W4410356879.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2112796928","https://openalex.org/W2909383239","https://openalex.org/W2914304175","https://openalex.org/W2962858109","https://openalex.org/W2963070905","https://openalex.org/W2963350370","https://openalex.org/W3035524453","https://openalex.org/W3044220283","https://openalex.org/W3138516171","https://openalex.org/W3142729297","https://openalex.org/W3203411656","https://openalex.org/W3204699193","https://openalex.org/W3205976355","https://openalex.org/W3212897593","https://openalex.org/W4226040249","https://openalex.org/W4283517970","https://openalex.org/W4300860215","https://openalex.org/W4312359569"],"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/W2546503577"],"abstract_inverted_index":{"Few-shot":[0],"classification":[1,71],"categorizes":[2],"objects":[3],"with":[4,23,114],"minimal":[5],"training":[6,60],"data,":[7],"making":[8,65],"it":[9],"valuable":[10],"when":[11],"large":[12,80],"datasets":[13,227],"are":[14,17,51],"impractical.":[15],"Models":[16],"trained":[18],"on":[19,30,61,79,110,148,224],"a":[20,31,41,183,208],"base":[21,47,63,106],"set":[22],"many":[24],"samples":[25,38],"per":[26,44],"class":[27,161,187],"and":[28,48,131,185,228],"tested":[29],"novel":[32,49,111],"set,":[33,64],"where":[34],"they":[35],"classify":[36],"new":[37],"using":[39,154],"only":[40],"few":[42],"examples":[43],"class.":[45],"Since":[46],"classes":[50,58],"distinct,":[52],"models":[53,101],"must":[54],"generalize":[55],"to":[56,86,104,128,142,175,193,230],"unseen":[57],"while":[59,189],"the":[62,105,125,140,144,168,180,191,205,215,232],"meta-learning":[66,85,95,126],"more":[67],"effective":[68,97],"than":[69],"traditional":[70],"methods.":[72],"State-of-the-art":[73],"techniques":[74,123],"improve":[75,132],"generalization":[76],"by":[77,83],"pretraining":[78],"datasets,":[81],"followed":[82],"applying":[84],"further":[87],"enhance":[88],"performance.":[89],"However,":[90],"we":[91,120,135,171],"argue":[92],"that":[93],"although":[94],"is":[96,152,201,211,217],"for":[98],"few-shot":[99],"tasks,":[100],"often":[102],"overfit":[103],"classes,":[107,112],"reducing":[108,179],"performance":[109],"even":[113],"pretraining.":[115],"To":[116],"address":[117],"this":[118],"issue,":[119],"propose":[121],"two":[122],"in":[124,157,164],"phase":[127],"reduce":[129],"overfitting":[130],"generalization.":[133],"First,":[134],"mask":[136],"important":[137],"parts":[138],"of":[139,195,204,234],"sample":[141,184],"prevent":[143],"model":[145,210],"from":[146],"over-relying":[147],"specific":[149],"features.":[150],"Masking":[151],"applied":[153],"attention":[155],"scores":[156],"ViT-like":[158],"backbones":[159],"or":[160,213,219],"activation":[162],"maps":[163],"CNN-based":[165],"backbones.":[166],"Using":[167],"masked":[169],"samples,":[170],"apply":[172],"contrastive":[173],"loss":[174],"prototypical":[176],"network":[177],"training,":[178],"distance":[181,192],"between":[182],"its":[186],"prototype":[188],"increasing":[190],"prototypes":[194],"other":[196],"classes.":[197],"The":[198],"proposed":[199],"method":[200],"applicable":[202],"regardless":[203],"backbone,":[206],"whether":[207,214],"pretrained":[209],"used,":[212],"approach":[216],"inductive":[218],"transductive.":[220],"We":[221],"conduct":[222],"experiments":[223],"various":[225],"benchmark":[226],"configurations":[229],"demonstrate":[231],"effectiveness":[233],"our":[235],"method.":[236]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}