{"id":"https://openalex.org/W4399658498","doi":"https://doi.org/10.1145/3641584.3641661","title":"I-YOLO: Improved Progressive Feature Pyramid and Wise-IOU for Object Detection","display_name":"I-YOLO: Improved Progressive Feature Pyramid and Wise-IOU for Object Detection","publication_year":2023,"publication_date":"2023-09-22","ids":{"openalex":"https://openalex.org/W4399658498","doi":"https://doi.org/10.1145/3641584.3641661"},"language":"en","primary_location":{"id":"doi:10.1145/3641584.3641661","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641584.3641661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Artificial Intelligence and Pattern Recognition (AIPR)","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/A5099124650","display_name":"Jinming Shi","orcid":"https://orcid.org/0009-0003-8526-1532"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinming Shi","raw_affiliation_strings":["CIIP: Center for image and Information Processin, Xi'an University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0009-0003-8526-1532","affiliations":[{"raw_affiliation_string":"CIIP: Center for image and Information Processin, Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088695502","display_name":"Fujie Yang","orcid":"https://orcid.org/0009-0001-3023-4882"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fujie Yang","raw_affiliation_strings":["CIIP: Center for image and Information Processin, Xi'an University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0009-0001-3023-4882","affiliations":[{"raw_affiliation_string":"CIIP: Center for image and Information Processin, Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091958563","display_name":"Qian Wang","orcid":"https://orcid.org/0000-0002-6009-5246"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Wang","raw_affiliation_strings":["CIIP: Center for image and Information Processin, Xi'an University of Posts and Telecommunications, China"],"raw_orcid":"https://orcid.org/0000-0002-6009-5246","affiliations":[{"raw_affiliation_string":"CIIP: Center for image and Information Processin, Xi'an University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I4210136859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210136859"],"apc_list":null,"apc_paid":null,"fwci":0.1064,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44401524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"517","last_page":"522"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9966999888420105,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7434300780296326},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.7421925663948059},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7395537495613098},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6471014022827148},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6192551851272583},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6117997169494629},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5438275337219238},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46736833453178406},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43571043014526367},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09023717045783997}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7434300780296326},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.7421925663948059},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7395537495613098},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6471014022827148},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6192551851272583},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6117997169494629},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5438275337219238},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46736833453178406},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43571043014526367},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09023717045783997},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3641584.3641661","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641584.3641661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Artificial Intelligence and Pattern Recognition (AIPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1483870316","https://openalex.org/W2090042335","https://openalex.org/W2102605133","https://openalex.org/W2565639579","https://openalex.org/W2570343428","https://openalex.org/W2963037989","https://openalex.org/W3194790201","https://openalex.org/W3195537687","https://openalex.org/W3210586215","https://openalex.org/W4240153047","https://openalex.org/W4320487943","https://openalex.org/W4376852379","https://openalex.org/W4386076325","https://openalex.org/W6631782140","https://openalex.org/W6730903564"],"related_works":["https://openalex.org/W4249847449","https://openalex.org/W44395729","https://openalex.org/W2765338038","https://openalex.org/W1496225612","https://openalex.org/W1523500768","https://openalex.org/W1566843515","https://openalex.org/W4206776094","https://openalex.org/W3121197456","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"The":[0],"YOLO":[1,37],"algorithm,":[2],"as":[3],"the":[4,35,79,82,86,91,106,119,125,129,132,142,177],"most":[5],"typical":[6],"representation":[7],"of":[8,81,131,147],"one-stage":[9],"object":[10,20],"detection":[11,31,45],"methods,":[12],"is":[13,47],"based":[14,62],"on":[15,63,141],"deep":[16],"neural":[17],"networks":[18],"for":[19,28],"recognition":[21],"and":[22,41,84,97,127,144,170],"localization,":[23],"achieving":[24],"real-time":[25],"performance":[26],"suitable":[27],"deployment":[29],"in":[30,39],"systems.":[32],"YOLOV7":[33],"outperforms":[34],"previous":[36],"series":[38],"accuracy":[40,46,130],"speed.":[42],"However,":[43],"its":[44],"still":[48],"not":[49],"very":[50],"impressive.":[51],"To":[52],"address":[53],"this":[54],"problem,":[55],"we":[56,66,117,135],"propose":[57,67],"an":[58],"improved":[59],"model":[60,83,126,179],"(I-YOLO)":[61],"YOLOV7.":[64],"First,":[65],"a":[68,74],"progressive":[69],"feature":[70],"pyramid":[71],"network":[72],"with":[73],"distillation":[75],"module,":[76],"which":[77],"improves":[78,172],"efficiency":[80],"at":[85],"same":[87],"time":[88],"can":[89],"reduce":[90],"semantic":[92],"gaps":[93],"between":[94],"non-adjacent":[95],"layers,":[96],"further":[98],"utilizes":[99],"adaptive":[100],"spatial":[101],"fusion":[102],"operations":[103],"to":[104,123],"alleviate":[105],"target":[107],"information":[108],"conflict":[109],"problem":[110],"when":[111],"fusing":[112],"features":[113],"across":[114],"layers.":[115],"Second,":[116],"introduce":[118],"Wise-IoU":[120],"loss":[121],"function":[122],"optimize":[124],"improve":[128],"algorithm.":[133],"Furthermore,":[134],"train":[136],"I-YOLO":[137,171],"from":[138],"scratch":[139],"only":[140],"2007":[143],"2012":[145],"datasets":[146,154],"PASCAL":[148],"VOC":[149],"without":[150],"using":[151],"any":[152],"other":[153],"or":[155],"pre-trained":[156],"weights.":[157],"Experimental":[158],"results":[159,163],"show":[160],"that":[161],"competitive":[162],"are":[164],"achieved:":[165],"55.9%":[166],"AP":[167],"(74.7%":[168],"AP50),":[169],"by":[173],"about":[174],"2.5%":[175],"over":[176],"baseline":[178],"(YOLOV7).":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}