{"id":"https://openalex.org/W4402915571","doi":"https://doi.org/10.1109/icip51287.2024.10647754","title":"Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compression","display_name":"Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compression","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402915571","doi":"https://doi.org/10.1109/icip51287.2024.10647754"},"language":"en","primary_location":{"id":"doi:10.1109/icip51287.2024.10647754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10647754","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 Image Processing (ICIP)","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/A5102503394","display_name":"Shiyu Qin","orcid":"https://orcid.org/0000-0002-7705-490X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shiyu Qin","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085669318","display_name":"Yimin Zhou","orcid":"https://orcid.org/0000-0001-8692-9635"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi-Min Zhou","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376310","display_name":"Jinpeng Wang","orcid":"https://orcid.org/0000-0001-6127-9146"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin-Peng Wang","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044915371","display_name":"Bin Chen","orcid":"https://orcid.org/0000-0003-3022-1931"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Chen","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113405421","display_name":"Bao-Yi An","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bao-Yi An","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023762528","display_name":"Tao Dai","orcid":"https://orcid.org/0000-0003-0594-6404"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Dai","raw_affiliation_strings":["Shenzhen University"],"affiliations":[{"raw_affiliation_string":"Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110158722","display_name":"Shu\u2013Tao Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu-Tao Xia","raw_affiliation_strings":["Tsinghua University,Tsinghua Shenzhen International Graduate School"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Tsinghua Shenzhen International Graduate School","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102503394"],"corresponding_institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.3121,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81951554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1767","last_page":"1773"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9941999912261963,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9941999912261963,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9797000288963318,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9699000120162964,"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":0.6336787939071655},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.5945972204208374},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.5384369492530823},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5220322608947754},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5025937557220459},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.49032333493232727},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.38756561279296875},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.17785519361495972},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15252429246902466},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.13614672422409058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6336787939071655},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.5945972204208374},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5384369492530823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5220322608947754},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5025937557220459},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.49032333493232727},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.38756561279296875},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.17785519361495972},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15252429246902466},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.13614672422409058},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip51287.2024.10647754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10647754","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 Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2030265202","https://openalex.org/W2785562966","https://openalex.org/W2963149687","https://openalex.org/W2982853315","https://openalex.org/W3003267478","https://openalex.org/W3034469748","https://openalex.org/W3179468628","https://openalex.org/W3202918664","https://openalex.org/W3206996732","https://openalex.org/W3212865599","https://openalex.org/W4223425316","https://openalex.org/W4230291482","https://openalex.org/W4312651322","https://openalex.org/W4388821432","https://openalex.org/W6694251005","https://openalex.org/W6754634825","https://openalex.org/W6843128308","https://openalex.org/W6954875051","https://openalex.org/W6973812890"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W3018365851","https://openalex.org/W3207484021","https://openalex.org/W2775347418","https://openalex.org/W2779427294","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W2069885731","https://openalex.org/W2563206327"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,37,103],"propose":[4],"a":[5,17,69],"progressive":[6],"learning":[7],"paradigm":[8],"for":[9,43,129],"transformer-based":[10,71],"variable-rate":[11],"image":[12,72,160,173],"compression.":[13],"Our":[14],"approach":[15],"covers":[16],"wide":[18],"range":[19],"of":[20,26,68,79,93,107,164],"compression":[21,73,91,174],"rates":[22],"with":[23,110,141],"the":[24,27,50,64,77,83,89,94,98,105,133,138,169],"assistance":[25],"Layer-adaptive":[28],"Prompt":[29],"Module":[30],"(LPM).":[31],"Inspired":[32],"by":[33],"visual":[34],"prompt":[35,108],"tuning,":[36],"use":[38],"LPM":[39],"to":[40,75,119],"extract":[41],"prompts":[42],"input":[44],"images":[45],"and":[46,53,82,147,167],"hidden":[47],"features":[48],"at":[49,137],"encoder":[51],"side":[52],"decoder":[54],"side,":[55],"respectively,":[56],"which":[57,85,125],"are":[58,126],"fed":[59],"as":[60],"additional":[61],"information":[62],"into":[63],"swin":[65],"transformer":[66],"layer":[67],"pre-trained":[70],"model":[74,154],"affect":[76],"allocation":[78],"attention":[80],"region":[81],"bits,":[84],"in":[86,144,150,162],"turn":[87],"changes":[88],"target":[90,131],"ratio":[92],"model.":[95],"To":[96],"ensure":[97],"network":[99],"is":[100],"more":[101],"lightweight,":[102],"involves":[104],"integration":[106],"networks":[109],"less":[111],"convolutional":[112],"layers.":[113],"Exhaustive":[114],"experiments":[115],"show":[116],"that":[117],"compared":[118],"methods":[120,161,175],"based":[121],"on":[122],"multiple":[123],"models,":[124],"optimized":[127],"separately":[128],"different":[130],"rates,":[132],"proposed":[134],"method":[135],"arrives":[136],"same":[139],"performance":[140,166],"80%":[142],"savings":[143,149],"parameter":[145],"storage":[146],"90%":[148],"datasets.":[151],"Meanwhile,":[152],"our":[153],"outperforms":[155],"all":[156],"current":[157],"variable":[158],"bitrate":[159,172],"terms":[163],"rate-distortion":[165],"approaches":[168],"state-of-the-art":[170],"fixed":[171],"trained":[176],"from":[177],"scratch.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}
