{"id":"https://openalex.org/W3009565265","doi":"https://doi.org/10.1109/wacv45572.2020.9093507","title":"Improving Object Detection with Inverted Attention","display_name":"Improving Object Detection with Inverted Attention","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3009565265","doi":"https://doi.org/10.1109/wacv45572.2020.9093507","mag":"3009565265"},"language":"en","primary_location":{"id":"doi:10.1109/wacv45572.2020.9093507","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077288556","display_name":"Zeyi Huang","orcid":"https://orcid.org/0009-0009-3221-2597"},"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":"Zeyi Huang","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019419036","display_name":"Wei Ke","orcid":"https://orcid.org/0000-0003-0952-0961"},"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":"Wei Ke","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050270789","display_name":"Dong Huang","orcid":"https://orcid.org/0000-0003-3923-8828"},"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":"Dong Huang","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077288556"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.6378,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.91530551,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"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":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":0.9983000159263611,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.7710009813308716},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7468435764312744},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6546893119812012},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6425008177757263},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6421127915382385},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6241438388824463},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6139076352119446},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5731159448623657},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49741867184638977},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.49452969431877136},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49078568816185},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48979973793029785},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4319632351398468},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2130843997001648},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06510737538337708}],"concepts":[{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.7710009813308716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7468435764312744},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6546893119812012},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6425008177757263},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6421127915382385},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6241438388824463},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6139076352119446},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5731159448623657},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49741867184638977},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.49452969431877136},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49078568816185},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48979973793029785},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4319632351398468},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2130843997001648},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06510737538337708},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv45572.2020.9093507","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.75,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1849277567","https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2123045220","https://openalex.org/W2295107390","https://openalex.org/W2407521645","https://openalex.org/W2561238782","https://openalex.org/W2570343428","https://openalex.org/W2607037079","https://openalex.org/W2613718673","https://openalex.org/W2747685395","https://openalex.org/W2792824754","https://openalex.org/W2798590501","https://openalex.org/W2883363148","https://openalex.org/W2884585870","https://openalex.org/W2894820835","https://openalex.org/W2905016238","https://openalex.org/W2950141105","https://openalex.org/W2950800384","https://openalex.org/W2955058313","https://openalex.org/W2962858109","https://openalex.org/W2963045696","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963382180","https://openalex.org/W2963420686","https://openalex.org/W2963516811","https://openalex.org/W2963681621","https://openalex.org/W2964242925","https://openalex.org/W2998508940","https://openalex.org/W3106250896","https://openalex.org/W4288325606","https://openalex.org/W6620707391","https://openalex.org/W6631782140","https://openalex.org/W6639102338","https://openalex.org/W6639204139","https://openalex.org/W6677995690","https://openalex.org/W6704278359","https://openalex.org/W6714138976","https://openalex.org/W6730179637","https://openalex.org/W6731892127","https://openalex.org/W6735463952","https://openalex.org/W6743440100","https://openalex.org/W6743731764","https://openalex.org/W6753388331","https://openalex.org/W6753412334","https://openalex.org/W6754852571","https://openalex.org/W6764322716","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2378211422","https://openalex.org/W2110523656","https://openalex.org/W4287991909","https://openalex.org/W4390721878"],"abstract_inverted_index":{"Improving":[0],"object":[1,80,134],"detectors":[2,14,81,183],"against":[3],"occlusion,":[4],"blur":[5],"and":[6,28,86,128,138,149,171],"noise":[7],"is":[8,20],"a":[9,83],"critical":[10],"step":[11],"to":[12,23,36,123],"deploy":[13],"in":[15,55,63],"real":[16],"applications.":[17],"Since":[18],"it":[19],"not":[21],"possible":[22],"exhaust":[24],"all":[25],"image":[26],"defects":[27],"occlusions":[29],"through":[30],"data":[31],"collection,":[32],"many":[33],"researchers":[34],"seek":[35],"generate":[37],"occluded":[38],"samples.":[39],"The":[40],"generated":[41],"hard":[42,65,162],"samples":[43,66],"are":[44,61],"either":[45],"images":[46],"or":[47],"feature":[48,117,136,154],"maps":[49,118],"with":[50,111],"coarse":[51],"patches":[52,70],"dropped":[53],"out":[54],"the":[56,95,103,108,121,147,153],"spatial":[57,148],"dimensions.":[58],"Significant":[59],"overheads":[60],"required":[62],"generating":[64],"and/or":[67],"estimating":[68],"drop-out":[69],"using":[71,82],"extra":[72,159,165],"network":[73,98,110,166],"branches.":[74],"In":[75],"this":[76],"paper,":[77],"we":[78],"improve":[79],"highly":[84],"efficient":[85],"fine-grain":[87],"mechanism":[88],"called":[89],"Inverted":[90],"Attention":[91],"(IA).":[92],"Different":[93],"from":[94],"original":[96],"detector":[97,109,122],"that":[99,177],"only":[100],"focuses":[101],"on":[102,116,132,161,184],"dominant":[104],"part":[105],"of":[106,152],"objects,":[107],"IA":[112],"iteratively":[113],"inverts":[114],"attention":[115,131,169],"which":[119],"pushes":[120],"discover":[124],"new":[125],"discriminative":[126],"clues":[127],"puts":[129],"more":[130],"complementary":[133],"parts,":[135],"channels":[137,150],"even":[139],"context.":[140],"Our":[141],"approach":[142,179],"(1)":[143],"operates":[144],"along":[145],"both":[146],"dimensions":[151],"maps;":[155],"(2)":[156],"requires":[157],"no":[158,164,172],"training":[160],"samples,":[163],"parameters":[167],"for":[168],"estimation,":[170],"testing":[173],"overheads.":[174],"Experiments":[175],"show":[176],"our":[178],"consistently":[180],"improved":[181],"state-of-the-art":[182],"benchmark":[185],"databases.":[186]},"counts_by_year":[{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}