{"id":"https://openalex.org/W2913012226","doi":"https://doi.org/10.48550/arxiv.1901.09891","title":"See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification","display_name":"See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification","alternate_titles":[],"publication_year":2019,"publication_date":"2019-01-26","ids":{"openalex":"https://openalex.org/W2913012226","doi":"https://doi.org/10.48550/arxiv.1901.09891","mag":"2913012226"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1901.09891","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.09891","pdf_url":"https://arxiv.org/pdf/1901.09891","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":null,"raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W2913012226"],"child_works_count":0,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1901.09891","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101742191","display_name":"Tao Hu","orcid":"https://orcid.org/0000-0002-1382-7213","observed_orcids":["https://orcid.org/0000-0002-1382-7213"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Hu, Tao","raw_affiliation_strings":["University of Chinese Academy of Sciences , Beijing","University of the Chinese Academy of Sciences;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences , Beijing","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"University of the Chinese Academy of Sciences;","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047226078","display_name":"Honggang Qi","orcid":"https://orcid.org/0000-0002-7947-1491","observed_orcids":["https://orcid.org/0000-0002-7947-1491"]},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Qi, Honggang","raw_affiliation_strings":["University of Chinese Academy of Sciences , Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences , Beijing","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huang, Qingming","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Huang, Qingming","raw_affiliation_strings":["University of Chinese Academy of Sciences , Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences , Beijing","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":null,"display_name":"Lu, Yan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Lu, Yan","raw_affiliation_strings":["Microsoft Research Asia , Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia , Beijing","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":332,"reviewed_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_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8871999979019165,"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":0.8871999979019165,"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":0.0869000032544136,"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":0.015599999576807022,"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/fine-grained-image-classification","display_name":"fine-grained image classification","score":0.9359999895095825},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.8989999890327454},{"id":"https://openalex.org/keywords/weakly-supervised-learning","display_name":"weakly supervised learning","score":0.9440000057220459},{"id":"https://openalex.org/keywords/attention-maps","display_name":"attention maps","score":0.9879999756813049},{"id":"https://openalex.org/keywords/object-localization","display_name":"object localization","score":0.44600000977516174}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9448654651641846},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8458071351051331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7554786205291748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7334680557250977},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5597888231277466},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5591697096824646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5268403887748718},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4995753765106201},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.47200536727905273},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4220818877220154},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4129483103752136},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2863582670688629}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1901.09891","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.09891","pdf_url":"https://arxiv.org/pdf/1901.09891","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":null,"raw_type":"text"},{"id":"mag:2913012226","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1901.09891.pdf","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},{"id":"doi:10.48550/arxiv.1901.09891","doi":"https://doi.org/10.48550/arxiv.1901.09891","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1901.09891","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1901.09891","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.09891","pdf_url":"https://arxiv.org/pdf/1901.09891","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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2913012226.pdf","grobid_xml":"https://content.openalex.org/works/W2913012226.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W56385144","https://openalex.org/W603908379","https://openalex.org/W639708223","https://openalex.org/W1496650988","https://openalex.org/W1686810756","https://openalex.org/W1797268635","https://openalex.org/W1846799578","https://openalex.org/W1898560071","https://openalex.org/W1928906481","https://openalex.org/W1955942245","https://openalex.org/W2088049833","https://openalex.org/W2097117768","https://openalex.org/W2101611867","https://openalex.org/W2102605133","https://openalex.org/W2104657103","https://openalex.org/W2138011018","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2295107390","https://openalex.org/W2479109623","https://openalex.org/W2520774990","https://openalex.org/W2593484309","https://openalex.org/W2604702198","https://openalex.org/W2606520630","https://openalex.org/W2737725206","https://openalex.org/W2746314669","https://openalex.org/W2746791238","https://openalex.org/W2763070548","https://openalex.org/W2773003563","https://openalex.org/W2798365843","https://openalex.org/W2807931652","https://openalex.org/W2883888092","https://openalex.org/W2891951760","https://openalex.org/W2895643041","https://openalex.org/W2949736877","https://openalex.org/W2962761264","https://openalex.org/W2963254727","https://openalex.org/W2963446712","https://openalex.org/W2963468256","https://openalex.org/W2963603913","https://openalex.org/W2963911037","https://openalex.org/W2964274719","https://openalex.org/W2964350570","https://openalex.org/W3209259379","https://openalex.org/W4394642372"],"related_works":["https://openalex.org/W3190048979","https://openalex.org/W4293195859","https://openalex.org/W4323824575","https://openalex.org/W3200765315","https://openalex.org/W4386938552","https://openalex.org/W4408977863","https://openalex.org/W3132090385","https://openalex.org/W4214940196","https://openalex.org/W4400988073","https://openalex.org/W3035753722"],"abstract_inverted_index":{"Data":[0,48],"augmentation":[1],"is":[2,32],"usually":[3],"adopted":[4],"to":[5,52,69,137],"increase":[6],"the":[7,16,54,71,82,99,106,123,140,146,161],"amount":[8],"of":[9,18,56,131],"training":[10,62],"data,":[11],"prevent":[12],"overfitting":[13],"and":[14,34,92,143],"improve":[15,145],"performance":[17],"deep":[19],"models.":[20],"However,":[21],"in":[22,102,150],"practice,":[23],"random":[24,29],"data":[25,57],"augmentation,":[26],"such":[27],"as":[28],"image":[30,83],"cropping,":[31],"low-efficiency":[33],"might":[35],"introduce":[36],"many":[37],"uncontrolled":[38],"background":[39],"noises.":[40],"In":[41,105,122],"this":[42],"paper,":[43],"we":[44,64,80],"propose":[45],"Weakly":[46],"Supervised":[47],"Augmentation":[49],"Network":[50],"(WS-DAN)":[51],"explore":[53],"potential":[55],"augmentation.":[58],"Specifically,":[59],"for":[60],"each":[61],"image,":[63],"first":[65,107],"generate":[66],"attention":[67,87,90,93,126],"maps":[68],"represent":[70],"object's":[72],"discriminative":[73,116],"parts":[74],"by":[75,85],"weakly":[76],"supervised":[77],"learning.":[78],"Next,":[79],"augment":[81],"guided":[84],"these":[86],"maps,":[88],"including":[89],"cropping":[91],"dropping.":[94],"The":[95],"proposed":[96],"WS-DAN":[97,159],"improves":[98],"classification":[100,154],"accuracy":[101],"two":[103],"folds.":[104],"stage,":[108,125],"images":[109],"can":[110],"be":[111,120],"seen":[112],"better":[113],"since":[114],"more":[115],"parts'":[117],"features":[118],"will":[119],"extracted.":[121],"second":[124],"regions":[127],"provide":[128],"accurate":[129],"location":[130],"object,":[132],"which":[133,164],"ensures":[134],"our":[135,158],"model":[136],"look":[138],"at":[139],"object":[141],"closer":[142],"further":[144],"performance.":[147],"Comprehensive":[148],"experiments":[149],"common":[151],"fine-grained":[152],"visual":[153],"datasets":[155],"show":[156],"that":[157],"surpasses":[160],"state-of-the-art":[162],"methods,":[163],"demonstrates":[165],"its":[166],"effectiveness.":[167]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2913012226","counts_by_year":[{"year":2026,"cited_by_count":21},{"year":2025,"cited_by_count":40},{"year":2024,"cited_by_count":59},{"year":2023,"cited_by_count":55},{"year":2022,"cited_by_count":60},{"year":2021,"cited_by_count":56},{"year":2020,"cited_by_count":33},{"year":2019,"cited_by_count":8}],"updated_date":"2026-11-21T10:27:49.728292","created_date":"2019-02-21T00:00:00"}
