{"id":"https://openalex.org/W2977418027","doi":"https://doi.org/10.1109/ijcnn.2019.8852250","title":"Training Deep Neural Networks with Adversarially Augmented Features for Small-scale Training Datasets","display_name":"Training Deep Neural Networks with Adversarially Augmented Features for Small-scale Training Datasets","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2977418027","doi":"https://doi.org/10.1109/ijcnn.2019.8852250","mag":"2977418027"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8852250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113447319","display_name":"Masato Ishii","orcid":null},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masato Ishii","raw_affiliation_strings":["Data Science Research Laboratories, NEC, Kawasaki, Japan"],"affiliations":[{"raw_affiliation_string":"Data Science Research Laboratories, NEC, Kawasaki, Japan","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052997603","display_name":"Atsushi Sato","orcid":"https://orcid.org/0000-0001-6888-4912"},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Sato","raw_affiliation_strings":["Data Science Research Laboratories, NEC, Kawasaki, Japan"],"affiliations":[{"raw_affiliation_string":"Data Science Research Laboratories, NEC, Kawasaki, Japan","institution_ids":["https://openalex.org/I118347220"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113447319"],"corresponding_institution_ids":["https://openalex.org/I118347220"],"apc_list":null,"apc_paid":null,"fwci":0.5824,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.76317688,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998999834060669,"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":0.9980999827384949,"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":0.9954000115394592,"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/training","display_name":"Training (meteorology)","score":0.9024914503097534},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7677013874053955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6801925301551819},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6307864189147949},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6064094305038452},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5662305355072021},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5427482724189758},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5314128994941711},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3506634831428528}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.9024914503097534},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7677013874053955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6801925301551819},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6307864189147949},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6064094305038452},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5662305355072021},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5427482724189758},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5314128994941711},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3506634831428528},{"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2019.8852250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W769612788","https://openalex.org/W1849277567","https://openalex.org/W1885185971","https://openalex.org/W1903029394","https://openalex.org/W1928419358","https://openalex.org/W1944615693","https://openalex.org/W1945616565","https://openalex.org/W1982925187","https://openalex.org/W1998808035","https://openalex.org/W2095705004","https://openalex.org/W2097117768","https://openalex.org/W2141125852","https://openalex.org/W2145287260","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2257483379","https://openalex.org/W2331143823","https://openalex.org/W2440384215","https://openalex.org/W2479750863","https://openalex.org/W2543927648","https://openalex.org/W2594477595","https://openalex.org/W2603766943","https://openalex.org/W2951751045","https://openalex.org/W2963108767","https://openalex.org/W2963207607","https://openalex.org/W2963959597","https://openalex.org/W2964040467","https://openalex.org/W6600213771","https://openalex.org/W6622262455","https://openalex.org/W6639204139","https://openalex.org/W6640425456","https://openalex.org/W6674330103","https://openalex.org/W6684191040","https://openalex.org/W6726983090","https://openalex.org/W6735249503"],"related_works":["https://openalex.org/W1629725936","https://openalex.org/W303964064","https://openalex.org/W2101017737","https://openalex.org/W2950066684","https://openalex.org/W2773120646","https://openalex.org/W3200739883","https://openalex.org/W3012234327","https://openalex.org/W2791691546","https://openalex.org/W3157439253","https://openalex.org/W3007495838"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,18,57,126],"propose":[4],"a":[5,128],"novel":[6],"method":[7,155],"to":[8,68,96,105,114,119,131,136],"train":[9],"deep":[10,162],"neural":[11,163],"networks":[12],"for":[13],"small-scale":[14],"training":[15,26,34,74],"dataset.":[16],"Since":[17],"focus":[19],"on":[20,148],"the":[21,25,31,40,69,78,89,92,108,111,116,133,143,158,161],"situation":[22],"in":[23,53],"which":[24,99],"dataset":[27],"is":[28,39,94],"limited,":[29],"increasing":[30],"number":[32],"of":[33,45,88,110,142,160],"data":[35,37,47,55],"by":[36,64,139],"augmentation":[38],"most":[41],"straight-forward":[42],"solution.":[43],"Instead":[44],"augmenting":[46],"at":[48,61],"an":[49],"input":[50],"layer":[51,63,130],"as":[52,81,123],"typical":[54],"augmentation,":[56],"adversarially":[58],"augment":[59],"features":[60,71,80],"hidden":[62],"adding":[65],"small":[66],"perturbations":[67],"original":[70,144],"extracted":[72],"from":[73],"data.":[75],"We":[76],"call":[77],"augmented":[79],"adversarial":[82,117,134],"features.":[83,145],"To":[84],"effectively":[85],"avoid":[86],"overfitting":[87],"trained":[90],"network,":[91],"perturbation":[93],"designed":[95,104],"be":[97,120,137],"adversarial,":[98],"means":[100],"that":[101,153],"they":[102],"are":[103],"significantly":[106],"change":[107],"output":[109],"network.":[112,164],"Moreover,":[113],"induce":[115],"feature":[118,135],"more":[121],"reasonable":[122],"real":[124],"data,":[125],"adopt":[127],"coefficient":[129],"constrain":[132],"represented":[138],"linear":[140],"combination":[141],"Experimental":[146],"results":[147],"several":[149],"benchmark":[150],"datasets":[151],"show":[152],"our":[154],"substantially":[156],"improves":[157],"performance":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}