{"id":"https://openalex.org/W3160331490","doi":"https://doi.org/10.1109/icpr48806.2021.9412492","title":"A Close Look at Deep Learning with Small Data","display_name":"A Close Look at Deep Learning with Small Data","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3160331490","doi":"https://doi.org/10.1109/icpr48806.2021.9412492","mag":"3160331490"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412492","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/11573/1705180","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090424086","display_name":"Lorenzo Brigato","orcid":"https://orcid.org/0000-0002-0872-069X"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Brigato","raw_affiliation_strings":["Sapienza University of Rome, Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026692089","display_name":"Luca Iocchi","orcid":"https://orcid.org/0000-0001-9057-8946"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Iocchi","raw_affiliation_strings":["Sapienza University of Rome, Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I861853513"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":188,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2490","last_page":"2497"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network 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/T10036","display_name":"Advanced Neural Network 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":0.9995999932289124,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9991000294685364,"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/mnist-database","display_name":"MNIST database","score":0.8636008501052856},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8408043384552002},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.7240966558456421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6239436268806458},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6155487895011902},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6129193902015686},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5726499557495117},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5501648783683777},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5253003239631653},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.41580480337142944}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.8636008501052856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8408043384552002},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.7240966558456421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6239436268806458},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6155487895011902},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6129193902015686},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5726499557495117},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5501648783683777},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5253003239631653},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.41580480337142944}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412492","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1705180","is_oa":true,"landing_page_url":"https://hdl.handle.net/11573/1705180","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:iris.uniroma1.it:11573/1705180","is_oa":true,"landing_page_url":"https://hdl.handle.net/11573/1705180","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1677182931","https://openalex.org/W1903029394","https://openalex.org/W2095705004","https://openalex.org/W2106525823","https://openalex.org/W2165698076","https://openalex.org/W2194775991","https://openalex.org/W2239639518","https://openalex.org/W2295582178","https://openalex.org/W2311523351","https://openalex.org/W2335728318","https://openalex.org/W2573779815","https://openalex.org/W2592929672","https://openalex.org/W2616180702","https://openalex.org/W2750384547","https://openalex.org/W2766196653","https://openalex.org/W2889798024","https://openalex.org/W2895531857","https://openalex.org/W2919115771","https://openalex.org/W2954996726","https://openalex.org/W2963037989","https://openalex.org/W2963716183","https://openalex.org/W2964121744","https://openalex.org/W2982278021","https://openalex.org/W2994872659","https://openalex.org/W2998768810","https://openalex.org/W3010290582","https://openalex.org/W3016548329","https://openalex.org/W3023371261","https://openalex.org/W3035352032","https://openalex.org/W3118608800","https://openalex.org/W4287661027","https://openalex.org/W6628973269","https://openalex.org/W6631190155","https://openalex.org/W6674330103","https://openalex.org/W6697274609","https://openalex.org/W6754509688","https://openalex.org/W6768106036","https://openalex.org/W6779695680"],"related_works":["https://openalex.org/W3156786002","https://openalex.org/W2915754718","https://openalex.org/W2597787948","https://openalex.org/W2947175736","https://openalex.org/W4299822940","https://openalex.org/W2279398222","https://openalex.org/W2551883569","https://openalex.org/W3116689448","https://openalex.org/W2791939363","https://openalex.org/W3000866861"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,24,46,89,121],"perform":[4,80],"a":[5,30,35,125,134],"wide":[6],"variety":[7],"of":[8,17,54,108,151],"experiments":[9],"with":[10,68],"different":[11],"deep":[12],"learning":[13],"architectures":[14],"on":[15,147],"datasets":[16],"limited":[18],"size.":[19],"According":[20],"to":[21],"our":[22],"study,":[23],"show":[25,47,90,122],"that":[26,48,91,123],"model":[27],"complexity":[28,62],"is":[29,118,140],"critical":[31],"factor":[32],"when":[33,116,138],"only":[34],"few":[36],"samples":[37,71],"per":[38],"class":[39],"are":[40,144],"available.":[41],"Differently":[42],"from":[43],"the":[44,52,55,106,148],"literature,":[45],"in":[49,66],"some":[50],"configurations,":[51],"state":[53],"art":[56],"can":[57,96],"be":[58],"improved":[59],"using":[60],"low":[61],"models.":[63],"For":[64],"instance,":[65],"problems":[67],"scarce":[69],"training":[70],"and":[72],"without":[73],"data":[74,94,111,117,139],"augmentation,":[75],"low-complexity":[76],"convolutional":[77],"neural":[78],"networks":[79],"comparably":[81],"well":[82],"or":[83],"better":[84],"than":[85],"state-of-the-art":[86],"architectures.":[87],"Moreover,":[88],"even":[92,137],"standard":[93],"augmentation":[95],"boost":[97],"recognition":[98],"performance":[99],"by":[100],"large":[101],"margins.":[102],"This":[103],"result":[104],"suggests":[105],"development":[107],"more":[109],"complex":[110],"generation/augmentation":[112],"pipelines":[113],"for":[114],"cases":[115],"limited.":[119],"Finally,":[120],"dropout,":[124],"widely":[126],"used":[127],"regularization":[128],"technique,":[129],"maintains":[130],"its":[131],"role":[132],"as":[133],"good":[135],"regularizer":[136],"scarce.":[141],"Our":[142],"findings":[143],"empirically":[145],"validated":[146],"sub-sampled":[149],"versions":[150],"popular":[152],"CIFAR-10,":[153],"Fashion-MNIST":[154],"and,":[155],"SVHN":[156],"benchmarks.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":28},{"year":2025,"cited_by_count":53},{"year":2024,"cited_by_count":40},{"year":2023,"cited_by_count":31},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":13}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}