{"id":"https://openalex.org/W3013431607","doi":"https://doi.org/10.1109/icassp40776.2020.9053994","title":"Attentive Cutmix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification","display_name":"Attentive Cutmix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3013431607","doi":"https://doi.org/10.1109/icassp40776.2020.9053994","mag":"3013431607"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053994","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053994","pdf_url":"https://ieeexplore.ieee.org/ielx7/9040208/9052899/09053994.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/9040208/9052899/09053994.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005579992","display_name":"Devesh Walawalkar","orcid":"https://orcid.org/0000-0001-9464-9027"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Devesh Walawalkar","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie Mellon University/Department of Electrical and Computer Engineering, Pittsburgh PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University/Department of Electrical and Computer Engineering, Pittsburgh PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066530136","display_name":"Zhiqiang Shen","orcid":"https://orcid.org/0000-0002-4560-5092"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiqiang Shen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie Mellon University/Department of Electrical and Computer Engineering, Pittsburgh PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University/Department of Electrical and Computer Engineering, Pittsburgh PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085241696","display_name":"Zechun Liu","orcid":"https://orcid.org/0000-0001-5856-2506"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zechun Liu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie Mellon University/Department of Electrical and Computer Engineering, Pittsburgh PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University/Department of Electrical and Computer Engineering, Pittsburgh PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057959136","display_name":"Marios Savvides","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marios Savvides","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie Mellon University/Department of Electrical and Computer Engineering, Pittsburgh PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University/Department of Electrical and Computer Engineering, Pittsburgh PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005579992"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.5888,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.68329289,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3642","last_page":"3646"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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":0.9990000128746033,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996999979019165,"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/discriminative-model","display_name":"Discriminative model","score":0.792121946811676},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7681698203086853},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.696334719657898},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6874560117721558},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6844767928123474},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.6711525917053223},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.6274878978729248},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5895965695381165},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5755120515823364},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4720281660556793},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46290266513824463},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4272690713405609},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4223417639732361},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.413756787776947},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4102157950401306},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06049448251724243}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.792121946811676},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7681698203086853},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.696334719657898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6874560117721558},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6844767928123474},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.6711525917053223},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.6274878978729248},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5895965695381165},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5755120515823364},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4720281660556793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46290266513824463},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4272690713405609},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4223417639732361},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.413756787776947},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4102157950401306},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06049448251724243},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053994","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053994","pdf_url":"https://ieeexplore.ieee.org/ielx7/9040208/9052899/09053994.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2003.13048","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.13048","pdf_url":"https://arxiv.org/pdf/2003.13048","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"mag:3013431607","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2003.13048.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-115093","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-115093","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-115093","is_oa":false,"landing_page_url":"http://www.scopus.com/record/display.url?eid=2-s2.0-85089227365&origin=inward","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"},{"id":"doi:10.48550/arxiv.2003.13048","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2003.13048","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/icassp40776.2020.9053994","is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053994","pdf_url":"https://ieeexplore.ieee.org/ielx7/9040208/9052899/09053994.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3013431607.pdf","grobid_xml":"https://content.openalex.org/works/W3013431607.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2746314669","https://openalex.org/W2752782242","https://openalex.org/W2890166761","https://openalex.org/W2899771611","https://openalex.org/W2943322963","https://openalex.org/W2955425717","https://openalex.org/W2962793481","https://openalex.org/W2963399829","https://openalex.org/W2963420686","https://openalex.org/W2963446712","https://openalex.org/W2963495494","https://openalex.org/W2963813458","https://openalex.org/W2963890275","https://openalex.org/W2992308087","https://openalex.org/W3022377928","https://openalex.org/W3118608800","https://openalex.org/W6684191040","https://openalex.org/W6743428213","https://openalex.org/W6745136726","https://openalex.org/W6750298367","https://openalex.org/W6754484989","https://openalex.org/W6756040250","https://openalex.org/W6762718338","https://openalex.org/W6765460459","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W2992308087","https://openalex.org/W3098217967","https://openalex.org/W2965379890","https://openalex.org/W2962961439","https://openalex.org/W3105979354","https://openalex.org/W2964014446","https://openalex.org/W2952582289","https://openalex.org/W3172120015","https://openalex.org/W2904487290","https://openalex.org/W2607758613","https://openalex.org/W2912861356","https://openalex.org/W2950328304","https://openalex.org/W3163883647","https://openalex.org/W2963074118","https://openalex.org/W2950794831","https://openalex.org/W2579994402","https://openalex.org/W2022432808","https://openalex.org/W2760575525","https://openalex.org/W2494699027","https://openalex.org/W2978485285"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNN)":[3],"are":[4,19],"capable":[5],"of":[6,29,61,65,160],"learning":[7],"robust":[8],"representation":[9],"with":[10,149],"different":[11],"regularization":[12],"methods":[13,46,172],"and":[14,137,170],"activations":[15],"as":[16,37],"convolutional":[17],"layers":[18],"spatially":[20],"correlated.":[21],"Based":[22],"on":[23,93,107,145],"this":[24,68,81],"property,":[25],"a":[26,87,113,154,174],"large":[27],"variety":[28],"regional":[30],"dropout":[31],"strategies":[32],"have":[33],"been":[34],"proposed,":[35],"such":[36],"Cutout":[38],"[1],":[39],"DropBlock":[40],"[2],":[41],"CutMix":[42,94,169],"[3],":[43],"etc.":[44],"These":[45],"aim":[47],"to":[48,52,135],"promote":[49],"the":[50,58,73,102,108,120,140,158,167],"network":[51],"generalize":[53],"better":[54],"by":[55,173],"partially":[56],"occluding":[57],"discriminative":[59,122],"parts":[60,123],"objects.":[62],"However,":[63],"all":[64],"them":[66],"perform":[67],"operation":[69],"randomly,":[70],"without":[71],"capturing":[72],"most":[74,103,121],"important":[75],"region(s)":[76],"within":[77],"an":[78,125],"object.":[79],"In":[80,96],"paper,":[82],"we":[83,100],"propose":[84],"Attentive":[85],"CutMix,":[86],"naturally":[88],"enhanced":[89],"augmentation":[90],"strategy":[91],"based":[92,106],"[3].":[95],"each":[97],"training":[98],"iteration,":[99],"choose":[101],"descriptive":[104],"regions":[105],"intermediate":[109],"attention":[110],"maps":[111],"from":[112],"feature":[114],"extractor,":[115],"which":[116,164],"enables":[117],"searching":[118],"for":[119],"in":[124],"image.":[126],"Our":[127],"proposed":[128,162],"method":[129],"is":[130],"simple":[131],"yet":[132],"effective,":[133],"easy":[134],"implement":[136],"can":[138],"boost":[139],"baseline":[141,168],"significantly.":[142],"Extensive":[143],"experiments":[144],"CIFAR-10/100,":[146],"ImageNet":[147],"datasets":[148],"various":[150],"CNN":[151],"architectures":[152],"(in":[153],"unified":[155],"setting)":[156],"demonstrate":[157],"effectiveness":[159],"our":[161],"method,":[163],"consistently":[165],"outperforms":[166],"other":[171],"significant":[175],"margin.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}