{"id":"https://openalex.org/W3173168108","doi":"https://doi.org/10.1145/3457682.3457740","title":"YOLO-Tight: an Efficient Dynamic Compression Method for YOLO Object Detection Networks","display_name":"YOLO-Tight: an Efficient Dynamic Compression Method for YOLO Object Detection Networks","publication_year":2021,"publication_date":"2021-02-26","ids":{"openalex":"https://openalex.org/W3173168108","doi":"https://doi.org/10.1145/3457682.3457740","mag":"3173168108"},"language":"en","primary_location":{"id":"doi:10.1145/3457682.3457740","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3457682.3457740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 13th International Conference on Machine Learning and Computing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101992481","display_name":"Wei Yan","orcid":"https://orcid.org/0000-0001-8119-1539"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Yan","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101437266","display_name":"Ting Liu","orcid":"https://orcid.org/0000-0002-6950-8086"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Liu","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101704886","display_name":"Yuzhuo Fu","orcid":"https://orcid.org/0000-0001-5516-3016"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuzhuo Fu","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"378","last_page":"384"},"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.7401167154312134},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6235633492469788},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.503621518611908},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.49121731519699097},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4434603750705719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42056846618652344},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.1308368444442749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401167154312134},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6235633492469788},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.503621518611908},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.49121731519699097},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4434603750705719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42056846618652344},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.1308368444442749},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"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:10.1145/3457682.3457740","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3457682.3457740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 13th International Conference on Machine Learning and Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G1101891495","display_name":null,"funder_award_id":"61977045","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1902934009","https://openalex.org/W2613718673","https://openalex.org/W2955863859","https://openalex.org/W2962851801","https://openalex.org/W2963122961","https://openalex.org/W2963346150","https://openalex.org/W2964719556","https://openalex.org/W2970738028","https://openalex.org/W3034971973","https://openalex.org/W3103461182","https://openalex.org/W6730382033","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2058170566","https://openalex.org/W2036807459","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2079911747"],"abstract_inverted_index":{"Deep":[0],"learning":[1,34],"algorithms":[2],"perform":[3],"well":[4],"in":[5,146],"the":[6,41,70,79,85,95,126,130,140,158],"field":[7],"of":[8,54,97,153],"object":[9],"detection.":[10],"Object":[11],"detection":[12],"networks":[13],"represented":[14],"by":[15,134],"YOLO,":[16],"SSD":[17],"and":[18,30,56,76,90,108,112,117,129,148],"faster-RCNN":[19],"have":[20],"achieved":[21],"excellent":[22],"performance":[23],"on":[24,40,157],"public":[25],"datasets":[26],"such":[27],"as":[28],"VOC":[29],"COCO.":[31],"However,":[32],"deep":[33],"models":[35],"are":[36],"difficult":[37],"to":[38,50,68,136,142],"deploy":[39],"edge":[42],"computing":[43,47],"platform":[44],"with":[45],"less":[46,92,154],"resources":[48],"due":[49],"its":[51],"huge":[52],"amount":[53],"parameters":[55],"computation.":[57,93],"In":[58,94],"this":[59,121],"paper,":[60],"we":[61,123],"propose":[62],"an":[63,150],"efficient":[64],"dynamic":[65],"sparsity":[66,116],"method":[67,101],"help":[69],"network":[71,86,128,133,141],"quickly":[72],"mine":[73],"important":[74],"parameters,":[75],"then":[77],"prune":[78,125],"unimportant":[80],"weight":[81],"channels,":[82],"which":[83],"makes":[84],"model":[87],"more":[88,103],"compact":[89],"consumes":[91],"case":[96],"high":[98],"sparsity,":[99],"our":[100],"is":[102],"robust":[104],"than":[105,155],"L1":[106],"regularization":[107,110],"other":[109],"forms,":[111],"can":[113,124],"achieve":[114,143],"better":[115],"pruning":[118],"effects.":[119],"Through":[120],"method,":[122],"YOLOv3":[127],"enhanced":[131],"YOLOv3-SPP3":[132],"up":[135],"90%.":[137],"This":[138],"allows":[139],"5\u00d7":[144],"reduction":[145],"FLOPs":[147],"maintain":[149],"accuracy":[151],"loss":[152],"1%":[156],"BDD100k":[159],"dataset.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}