{"id":"https://openalex.org/W2598097916","doi":null,"title":"Multi-Scale Dense Convolutional Networks for Efficient Prediction.","display_name":"Multi-Scale Dense Convolutional Networks for Efficient Prediction.","publication_year":2017,"publication_date":"2017-03-29","ids":{"openalex":"https://openalex.org/W2598097916","mag":"2598097916"},"language":"en","primary_location":{"id":"mag:2598097916","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1703.09844v2","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/1703.09844v2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013240918","display_name":"Gao Ming Huang","orcid":"https://orcid.org/0000-0002-7251-0988","observed_orcids":["https://orcid.org/0000-0002-7251-0988","https://orcid.org/0000-0002-0003-0184"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao Huang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-7251-0988","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074311082","display_name":"Danlu Chen","orcid":"https://orcid.org/0000-0002-8582-8151","observed_orcids":["https://orcid.org/0000-0002-8582-8151"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Danlu Chen","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8582-8151","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101928475","display_name":"Tianhong Li","orcid":"https://orcid.org/0000-0001-6280-6411","observed_orcids":["https://orcid.org/0000-0001-6280-6411"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianhong Li","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6280-6411","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074393700","display_name":"Felix Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felix Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109065097","display_name":"Laurens J. P. van der Maaten","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laurens van der Maaten","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5006380227","display_name":"Kilian Q. Weinberger","orcid":"https://orcid.org/0009-0008-9313-7239","observed_orcids":["https://orcid.org/0009-0008-9313-7239"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kilian Q. Weinberger","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":108,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0,"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/early-exit-networks","display_name":"early-exit networks","score":0.7210000157356262},{"id":"https://openalex.org/keywords/dense-connections","display_name":"dense connections","score":0.6010000109672546},{"id":"https://openalex.org/keywords/multiscale-convolutional-neural-network","display_name":"multi-scale convolutional neural network","score":0.8349999785423279},{"id":"https://openalex.org/keywords/resource-constrained-inference","display_name":"resource-constrained inference","score":0.7120000123977661},{"id":"https://openalex.org/keywords/computational-efficiency","display_name":"computational efficiency","score":0.4020000100135803},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.8320000171661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7982394695281982},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.750458300113678},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6998358964920044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6423500776290894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5335014462471008},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5333120226860046},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.48153024911880493},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4747626781463623},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.459855854511261},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4526585638523102},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4211184084415436},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3960198163986206},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39264360070228577},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1763005554676056},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2598097916","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1703.09844v2","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2598097916","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1703.09844v2","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2767421475","https://openalex.org/W4390190323","https://openalex.org/W1563795667","https://openalex.org/W2887340149","https://openalex.org/W7056234997","https://openalex.org/W2900075744","https://openalex.org/W2996151060","https://openalex.org/W3092739317","https://openalex.org/W300523764","https://openalex.org/W7096967739"],"abstract_inverted_index":{"In":[0,70],"this":[1],"paper":[2],"we":[3,101,114,139],"investigate":[4],"image":[5],"classification":[6,136],"with":[7,96,129],"computational":[8],"resource":[9,98],"limits":[10],"at":[11,38],"test":[12,27,105],"time.":[13,106],"Two":[14],"such":[15,76],"settings":[16],"are:":[17],"1.":[18],"anytime":[19],"classification,":[20,45],"where":[21,46],"the":[22,33,78,112,154,167],"network's":[23],"prediction":[24,37],"for":[25],"a":[26,36,47,56,120,141],"example":[28],"is":[29,52,86],"progressively":[30],"updated,":[31],"facilitating":[32],"output":[34],"of":[35,50,58],"any":[39],"time;":[40],"and":[41,67,81,126,149],"2.":[42],"budgeted":[43],"batch":[44],"fixed":[48],"amount":[49],"computation":[51,110],"available":[53],"to":[54,72],"classify":[55],"set":[57],"examples":[59],"that":[60,146,162],"can":[61],"be":[62],"spent":[63],"unevenly":[64],"across":[65],"easier":[66],"harder":[68],"inputs.":[69],"contrast":[71],"most":[73],"prior":[74],"work,":[75],"as":[77,117],"popular":[79],"Viola":[80],"Jones":[82],"algorithm,":[83],"our":[84,163],"approach":[85],"based":[87],"on":[88,157],"convolutional":[89,123],"neural":[90,124],"networks.":[91],"We":[92],"train":[93],"multiple":[94],"classifiers":[95],"varying":[97],"demands,":[99],"which":[100],"adaptively":[102],"apply":[103],"during":[104],"To":[107,132],"maximally":[108],"re-use":[109],"between":[111],"classifiers,":[113],"incorporate":[115],"them":[116,128],"early-exits":[118],"into":[119],"single":[121],"deep":[122],"network":[125,144],"inter-connect":[127],"dense":[130],"connectivity.":[131],"facilitate":[133],"high":[134],"quality":[135],"early":[137],"on,":[138],"use":[140],"two-dimensional":[142],"multi-scale":[143],"architecture":[145],"maintains":[147],"coarse":[148],"fine":[150],"level":[151],"features":[152],"all-throughout":[153],"network.":[155],"Experiments":[156],"three":[158],"image-classification":[159],"tasks":[160],"demonstrate":[161],"framework":[164],"substantially":[165],"improves":[166],"existing":[168],"state-of-the-art":[169],"in":[170],"both":[171],"settings.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":29},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":5}],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2017-04-07T00:00:00"}