{"id":"https://openalex.org/W2268574989","doi":null,"title":"Obtaining Better Image Representations by Combining Complementary Activation Features of Multiple ConvNet Layers for Transfer Learning","display_name":"Obtaining Better Image Representations by Combining Complementary Activation Features of Multiple ConvNet Layers for Transfer Learning","publication_year":2016,"publication_date":"2016-02-01","ids":{"openalex":"https://openalex.org/W2268574989","mag":"2268574989"},"language":"en","primary_location":{"id":"mag:2268574989","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1602.00417","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/pdf/1602.00417","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037862489","display_name":"Jumabek Alikhanov","orcid":"https://orcid.org/0000-0003-3103-6033","observed_orcids":["https://orcid.org/0000-0003-3103-6033"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jumabek Alikhanov","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3103-6033","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082745934","display_name":"SeungYon Ko","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"SeungYon Ko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5114032705","display_name":"Geun Sik Jo","orcid":"https://orcid.org/0000-0003-4477-0755","observed_orcids":["https://orcid.org/0000-0003-4477-0755"]},"institutions":[{"id":"https://openalex.org/I191879574","display_name":"Inha University","ror":"https://ror.org/01easw929","country_code":"KR","type":"education","lineage":["https://openalex.org/I191879574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Geun Sik Jo","raw_affiliation_strings":["Inha University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inha University,","institution_ids":["https://openalex.org/I191879574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9814000129699707,"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":0.9814000129699707,"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":0.01549999974668026,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0013000000035390258,"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/transfer-learning","display_name":"transfer learning","score":0.9620000123977661},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.9120000004768372},{"id":"https://openalex.org/keywords/image-representation","display_name":"image representation","score":0.7250000238418579},{"id":"https://openalex.org/keywords/feature-combination","display_name":"feature combination","score":0.7960000038146973},{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.9639999866485596},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.6499999761581421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7941270470619202},{"id":"https://openalex.org/C141404830","wikidata":"https://www.wikidata.org/wiki/Q2823869","display_name":"AdaBoost","level":3,"score":0.7839556932449341},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.7445731163024902},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7257357835769653},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6616005301475525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5795142650604248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4999504089355469},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.45289814472198486},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4199492335319519},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2268574989","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1602.00417","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:2268574989","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1602.00417","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W3968525","https://openalex.org/W204268067","https://openalex.org/W613766092","https://openalex.org/W1563088657","https://openalex.org/W1574818812","https://openalex.org/W1576445103","https://openalex.org/W1849277567","https://openalex.org/W2017814585","https://openalex.org/W2032210760","https://openalex.org/W2037227137","https://openalex.org/W2062118960","https://openalex.org/W2102605133","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2124386111","https://openalex.org/W2134670479","https://openalex.org/W2145073242","https://openalex.org/W2155541015","https://openalex.org/W2155893237","https://openalex.org/W2161381512","https://openalex.org/W2161969291","https://openalex.org/W2184241488","https://openalex.org/W2203224402","https://openalex.org/W2911964244"],"related_works":["https://openalex.org/W2323711196","https://openalex.org/W2203224402","https://openalex.org/W2994524537","https://openalex.org/W6999536648","https://openalex.org/W2552561459","https://openalex.org/W2887135589","https://openalex.org/W4220657935","https://openalex.org/W4287833018","https://openalex.org/W7139236116","https://openalex.org/W2909101896"],"abstract_inverted_index":{"Convolutional":[0],"Networks":[1],"(ConvNets)":[2],"are":[3],"powerful":[4],"models":[5],"that":[6,179],"learn":[7],"hierarchies":[8],"of":[9,48,60,78,93,134,165,199],"visual":[10],"features,":[11],"which":[12],"could":[13],"also":[14,209],"be":[15],"used":[16],"as":[17,56],"an":[18,61],"image":[19,63],"representations":[20],"in":[21,97,111],"transfer":[22,28,80,101,171],"learning.":[23,102,172],"The":[24],"Basic":[25],"pipeline":[26],"for":[27,64,118],"learning":[29,81],"is":[30,73,88],"to":[31,74,145,160,177],"first":[32],"train":[33,210],"a":[34,37,53,57,76,220],"ConvNet":[35,84,94,115,126,154,166,187,192,205,224,230],"on":[36,90],"large":[38],"dataset":[39,67],"(source":[40],"task)":[41],"and":[42],"then":[43],"use":[44,142,174],"feed-forward":[45],"units":[46],"activation":[47],"the":[49,91,135,152,197],"trained":[50],"network,":[51],"at":[52],"certain":[54],"layer,":[55],"generic":[58],"representation":[59],"input":[62],"another":[65],"smaller":[66],"(target":[68],"task).":[69],"Our":[70,157],"key":[71],"contribution":[72],"introduce":[75],"notion":[77],"better":[79,109],"using":[82],"multiple":[83,125,223],"layer":[85,116,127,167,225,231],"features.":[86,156,194,232],"Idea":[87],"based":[89],"difference":[92],"Layer":[95,155,188,193,206],"features":[96,117,128,137,149,168,189,207,226],"describing":[98],"images":[99],"when":[100,169],"We":[103,141,173],"demonstrate":[104],"this":[105,162],"idea":[106],"by":[107,129],"achieving":[108],"performance":[110],"classification":[112],"against":[113,190],"single":[114],"three":[119],"standard":[120],"datasets.":[121],"When":[122],"we":[123,208],"combine":[124],"simply":[130],"concatenating":[131],"them,":[132],"most":[133],"resulting":[136],"would":[138],"become":[139],"repetitive.":[140],"AdaBoost.MH":[143,175,218],"classifier":[144,176],"implicitly":[146],"select":[147],"distinct":[148],"from":[150],"among":[151,203],"combined":[153,204,222],"experiments":[158,216],"intends":[159],"show":[161,178],"complementary":[163],"nature":[164],"doing":[170],"one":[180],"can":[181],"achieve":[182],"superior":[183],"results":[184],"with":[185,217],"Combined":[186],"individual":[191],"To":[195],"emphasize":[196],"importance":[198],"careful":[200],"feature":[201],"selection":[202],"linear":[211],"SVM":[212],"classifier.":[213],"In":[214],"our":[215],"being":[219],"classifier,":[221],"always":[227],"outperform":[228],"Single":[229]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}