{"id":"https://openalex.org/W4402595239","doi":"https://doi.org/10.1109/avss61716.2024.10672579","title":"Revisiting Layer-level Residual Connections for Efficient Object Detection","display_name":"Revisiting Layer-level Residual Connections for Efficient Object Detection","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402595239","doi":"https://doi.org/10.1109/avss61716.2024.10672579"},"language":"en","primary_location":{"id":"doi:10.1109/avss61716.2024.10672579","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/avss61716.2024.10672579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)","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/A5101953394","display_name":"Jong-Ryul Lee","orcid":"https://orcid.org/0000-0003-0774-3619"},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jong-Ryul Lee","raw_affiliation_strings":["Chungnam National University,Daejeon,Korea"],"affiliations":[{"raw_affiliation_string":"Chungnam National University,Daejeon,Korea","institution_ids":["https://openalex.org/I196345858"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063300693","display_name":"Yong-Hyuk Moon","orcid":"https://orcid.org/0000-0002-6700-1070"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yong-Hyuk Moon","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI),Daejeon,Korea"],"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI),Daejeon,Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101953394"],"corresponding_institution_ids":["https://openalex.org/I196345858"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.155178,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"139","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9833999872207642,"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":0.9833999872207642,"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":0.9718999862670898,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9567999839782715,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.7156963348388672},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.6693755388259888},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6309136748313904},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5365580916404724},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33646562695503235},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3247895836830139},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17582035064697266},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.11370977759361267}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7156963348388672},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6693755388259888},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6309136748313904},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5365580916404724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33646562695503235},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3247895836830139},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17582035064697266},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.11370977759361267},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/avss61716.2024.10672579","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/avss61716.2024.10672579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2056760934","https://openalex.org/W2194775991","https://openalex.org/W2570343428","https://openalex.org/W2796970379","https://openalex.org/W2962677625","https://openalex.org/W2963122961","https://openalex.org/W2963163009","https://openalex.org/W2963323244","https://openalex.org/W2963446712","https://openalex.org/W2981884310","https://openalex.org/W2981985696","https://openalex.org/W3034342078","https://openalex.org/W3034674511","https://openalex.org/W3113223504","https://openalex.org/W3176411177","https://openalex.org/W3205100603","https://openalex.org/W4307545940","https://openalex.org/W4386076325","https://openalex.org/W4386083031","https://openalex.org/W6628973269","https://openalex.org/W6638523607","https://openalex.org/W6686583229","https://openalex.org/W6729059855","https://openalex.org/W6730637201","https://openalex.org/W6737664043","https://openalex.org/W6749959846","https://openalex.org/W6750227808","https://openalex.org/W6755838813","https://openalex.org/W6762718338","https://openalex.org/W6763207085","https://openalex.org/W6765643347","https://openalex.org/W6777046832","https://openalex.org/W6783189819","https://openalex.org/W6793164127","https://openalex.org/W6796978233","https://openalex.org/W6843239693"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Modern":[0],"neural":[1,49,68],"network":[2,69],"models":[3,153],"commonly":[4],"have":[5],"residual":[6,52],"connections,":[7],"because":[8],"they":[9],"are":[10],"helpful":[11],"to":[12,17,23,41,144],"achieve":[13,24],"better":[14,26],"performance.":[15],"Due":[16],"their":[18,56],"unconditional":[19],"popularity,":[20],"modifying":[21],"them":[22],"a":[25,48,64,75,87],"efficiency-accuracy":[27],"trade-off":[28],"is":[29],"rarely":[30],"studied":[31],"in":[32,140],"the":[33,94,97,104,111,128,136],"literature.":[34],"Motivated":[35],"by":[36,46,81],"this,":[37,61],"we":[38,62,73,99],"study":[39],"how":[40],"get":[42],"an":[43],"efficient":[44],"sub-network":[45],"rewiring":[47,70,84],"block":[50],"having":[51],"connections":[53],"based":[54],"on":[55,60],"inference":[57],"paths.":[58],"Based":[59],"devise":[63],"new":[65],"simulated":[66],"annealing-based":[67],"method.":[71,91],"Then,":[72],"construct":[74],"simple":[76],"yet":[77],"effective":[78],"compression":[79],"pipeline":[80,133],"combining":[82],"this":[83],"method":[85,138,148],"and":[86,107,122],"recent":[88],"channel":[89],"pruning":[90,137],"To":[92],"demonstrate":[93,130],"effectiveness":[95],"of":[96,127],"pipeline,":[98],"use":[100],"object":[101],"detection":[102],"as":[103,110],"target":[105,112],"task":[106],"consider":[108],"YOLOv8":[109,145],"model.":[113],"We":[114],"conduct":[115],"experiments":[116,129],"with":[117],"two":[118],"well-known":[119],"datasets:":[120],"VisDrone":[121],"PASCAL":[123],"VOC.":[124],"The":[125],"results":[126],"that":[131],"our":[132,147],"successfully":[134],"outperforms":[135],"alone":[139],"most":[141],"cases.":[142],"Compared":[143],"series,":[146],"can":[149],"offer":[150],"more":[151],"accurate":[152],"for":[154],"VisDrone.":[155]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}