{"id":"https://openalex.org/W2903048756","doi":"https://doi.org/10.48550/arxiv.1811.10725","title":"MIST: Multiple Instance Spatial Transformer Network","display_name":"MIST: Multiple Instance Spatial Transformer Network","publication_year":2018,"publication_date":"2018-11-26","ids":{"openalex":"https://openalex.org/W2903048756","doi":"https://doi.org/10.48550/arxiv.1811.10725","mag":"2903048756"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1811.10725","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.10725","pdf_url":"https://arxiv.org/pdf/1811.10725","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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.10725","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059111697","display_name":"Baptiste Angles","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Angles, Baptiste","raw_affiliation_strings":["University of Victoria ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria ,","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088242090","display_name":"Yuhe Jin","orcid":"https://orcid.org/0000-0002-0002-1384","observed_orcids":["https://orcid.org/0000-0002-0002-1384"]},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jin, Yuhe","raw_affiliation_strings":["University of British Columbia ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia ,","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042760897","display_name":"Simon Kornblith","orcid":"https://orcid.org/0000-0002-9088-2443","observed_orcids":["https://orcid.org/0000-0002-9088-2443"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kornblith, Simon","raw_affiliation_strings":["Google Research ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research ,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037094498","display_name":"Andrea Tagliasacchi","orcid":"https://orcid.org/0000-0002-2209-7187","observed_orcids":["https://orcid.org/0000-0002-2209-7187"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tagliasacchi, Andrea","raw_affiliation_strings":["Google Research ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research ,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049893251","display_name":"Kwang Moo Yi","orcid":"https://orcid.org/0000-0001-9036-3822","observed_orcids":["https://orcid.org/0000-0001-9036-3822"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi, Kwang Moo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.5210000276565552,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.5210000276565552,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.4408999979496002,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.01720000058412552,"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/multiple-instance-learning","display_name":"multiple instance learning","score":0.8220000267028809},{"id":"https://openalex.org/keywords/spatial-transformer-network","display_name":"spatial transformer network","score":0.7689999938011169},{"id":"https://openalex.org/keywords/slack-variables","display_name":"slack variables","score":0.5550000071525574},{"id":"https://openalex.org/keywords/multi-stage-training","display_name":"multi-stage training","score":0.8199999928474426},{"id":"https://openalex.org/keywords/image-reconstruction","display_name":"image reconstruction","score":0.8529999852180481},{"id":"https://openalex.org/keywords/object-localization","display_name":"object localization","score":0.6119999885559082},{"id":"https://openalex.org/keywords/autoencoder","display_name":"autoencoder","score":0.6029999852180481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7814316153526306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7106471061706543},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5933501720428467},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5299797058105469},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5144231915473938},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.4671798348426819},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44039687514305115},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.4364451766014099},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07678234577178955},{"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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1811.10725","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.10725","pdf_url":"https://arxiv.org/pdf/1811.10725","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:2903048756","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1811.10725.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.1811.10725","doi":"https://doi.org/10.48550/arxiv.1811.10725","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1811.10725","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:1811.10725","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.10725","pdf_url":"https://arxiv.org/pdf/1811.10725","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":[{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2903048756.pdf","grobid_xml":"https://content.openalex.org/works/W2903048756.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W639708223","https://openalex.org/W1484210532","https://openalex.org/W1677182931","https://openalex.org/W1677409904","https://openalex.org/W1850742715","https://openalex.org/W2046033161","https://openalex.org/W2061987443","https://openalex.org/W2077205830","https://openalex.org/W2097073572","https://openalex.org/W2151103935","https://openalex.org/W2168356304","https://openalex.org/W2295107390","https://openalex.org/W2307770531","https://openalex.org/W2469784314","https://openalex.org/W2616247523","https://openalex.org/W2749210894","https://openalex.org/W2775929773","https://openalex.org/W2789071950","https://openalex.org/W2792824754","https://openalex.org/W2795124604","https://openalex.org/W2798748179","https://openalex.org/W2798814244","https://openalex.org/W2804394440","https://openalex.org/W2807931652","https://openalex.org/W2812468425","https://openalex.org/W2895236117","https://openalex.org/W2949896259","https://openalex.org/W2951132567","https://openalex.org/W2951548327","https://openalex.org/W2962730651","https://openalex.org/W2962876901","https://openalex.org/W2963184176","https://openalex.org/W2963264960","https://openalex.org/W2963419579","https://openalex.org/W2963758027","https://openalex.org/W6926480584"],"related_works":["https://openalex.org/W4394645265","https://openalex.org/W3170152225","https://openalex.org/W2922495351","https://openalex.org/W1484210532","https://openalex.org/W2737326572","https://openalex.org/W2902488667","https://openalex.org/W4303474916","https://openalex.org/W2949150497","https://openalex.org/W7097173297","https://openalex.org/W4409357581"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,44,55,64,90,95],"deep":[3],"network":[4,30,46,65],"that":[5,16],"can":[6,121],"be":[7],"trained":[8],"to":[9,32,43,53,105,107,117,124],"tackle":[10],"image":[11],"reconstruction":[12],"and":[13,39,138],"classification":[14],"problems":[15],"involve":[17],"detection":[18],"of":[19,86,133],"multiple":[20],"object":[21,135],"instances,":[22],"without":[23],"any":[24],"supervision":[25],"regarding":[26],"their":[27],"whereabouts.":[28],"The":[29,59],"learns":[31],"extract":[33],"the":[34,67,78,84,112,131,134,144],"most":[35],"significant":[36],"top-K":[37,69,87],"patches,":[38],"feeds":[40],"these":[41],"patches":[42],"task-specific":[45],"--":[47,52],"e.g.,":[48],"auto-encoder":[49],"or":[50],"classifier":[51],"solve":[54],"domain":[56],"specific":[57],"problem.":[58],"challenge":[60],"in":[61,94,111,139],"training":[62,79,113],"such":[63],"is":[66,103,136],"non-differentiable":[68],"selection":[70,88],"process.":[71],"To":[72],"address":[73],"this":[74],"issue,":[75],"we":[76],"lift":[77],"optimization":[80],"problem":[81],"by":[82,115],"treating":[83],"result":[85],"as":[89],"slack":[91],"variable,":[92],"resulting":[93],"simple,":[96],"yet":[97],"effective,":[98],"multi-stage":[99],"training.":[100],"Our":[101],"method":[102],"able":[104],"learn":[106,123],"detect":[108],"recurrent":[109],"structures":[110,126],"dataset":[114],"learning":[116],"reconstruct":[118],"images.":[119],"It":[120],"also":[122],"localize":[125],"when":[127],"only":[128],"knowledge":[129],"on":[130],"occurrence":[132],"provided,":[137],"doing":[140],"so":[141],"it":[142],"outperforms":[143],"state-of-the-art.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2018-12-11T00:00:00"}