{"id":"https://openalex.org/W4392903172","doi":"https://doi.org/10.1109/icassp48485.2024.10447893","title":"Image Augmentation with Controlled Diffusion for Weakly-Supervised Semantic Segmentation","display_name":"Image Augmentation with Controlled Diffusion for Weakly-Supervised Semantic Segmentation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903172","doi":"https://doi.org/10.1109/icassp48485.2024.10447893"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447893","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102088294","display_name":"Wangyu Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]},{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN","GB"],"is_corresponding":true,"raw_author_name":"Wangyu Wu","raw_affiliation_strings":["Xi’an Jiaotong-Liverpool University","The University of Liverpool"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong-Liverpool University","institution_ids":["https://openalex.org/I69356397"]},{"raw_affiliation_string":"The University of Liverpool","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043844098","display_name":"Tianhong Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I195460627","display_name":"University of Aberdeen","ror":"https://ror.org/016476m91","country_code":"GB","type":"education","lineage":["https://openalex.org/I195460627"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tianhong Dai","raw_affiliation_strings":["University of Aberdeen"],"affiliations":[{"raw_affiliation_string":"University of Aberdeen","institution_ids":["https://openalex.org/I195460627"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020085889","display_name":"Xiaowei Huang","orcid":"https://orcid.org/0000-0001-6267-0366"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaowei Huang","raw_affiliation_strings":["The University of Liverpool"],"affiliations":[{"raw_affiliation_string":"The University of Liverpool","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113773882","display_name":"Fei Ma","orcid":"https://orcid.org/0000-0003-2563-3296"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Ma","raw_affiliation_strings":["Xi’an Jiaotong-Liverpool University"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong-Liverpool University","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011918180","display_name":"Jimin Xiao","orcid":"https://orcid.org/0000-0002-9416-2486"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jimin Xiao","raw_affiliation_strings":["Xi’an Jiaotong-Liverpool University"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong-Liverpool University","institution_ids":["https://openalex.org/I69356397"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102088294"],"corresponding_institution_ids":["https://openalex.org/I146655781","https://openalex.org/I69356397"],"apc_list":null,"apc_paid":null,"fwci":6.8496,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.97741617,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6175","last_page":"6179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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":0.9991999864578247,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8026951551437378},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.7111788392066956},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6734305620193481},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6487830281257629},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.634632408618927},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.6150275468826294},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5866766571998596},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5303602814674377},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.46399328112602234},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4569573402404785},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.4529817998409271},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.4419512450695038},{"id":"https://openalex.org/keywords/image-texture","display_name":"Image texture","score":0.4185551106929779},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.416171133518219},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40429452061653137},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38444533944129944},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10721036791801453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8026951551437378},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.7111788392066956},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6734305620193481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6487830281257629},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.634632408618927},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.6150275468826294},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5866766571998596},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5303602814674377},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.46399328112602234},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4569573402404785},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.4529817998409271},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.4419512450695038},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.4185551106929779},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.416171133518219},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40429452061653137},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38444533944129944},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10721036791801453},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447893","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1794522962","display_name":null,"funder_award_id":"61972323","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5539584389","display_name":null,"funder_award_id":"YZCXPT2022103","funder_id":"https://openalex.org/F4320324032","funder_display_name":"Xi\u2019an Jiaotong-Liverpool University"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","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"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320324032","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2031489346","https://openalex.org/W2129069237","https://openalex.org/W2144794286","https://openalex.org/W2145023731","https://openalex.org/W2306289963","https://openalex.org/W2962730651","https://openalex.org/W3034373787","https://openalex.org/W3036167779","https://openalex.org/W3094502228","https://openalex.org/W3110257065","https://openalex.org/W3121370741","https://openalex.org/W4224932468","https://openalex.org/W4286905173","https://openalex.org/W4312509967","https://openalex.org/W4312680544","https://openalex.org/W4312836939","https://openalex.org/W4312933868","https://openalex.org/W4313153210","https://openalex.org/W4390873054","https://openalex.org/W6679045638","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6786375611"],"related_works":["https://openalex.org/W4360784979","https://openalex.org/W2204605857","https://openalex.org/W1996489018","https://openalex.org/W2007664797","https://openalex.org/W3196005494","https://openalex.org/W2120981610","https://openalex.org/W3129669851","https://openalex.org/W2069318476","https://openalex.org/W2131637713","https://openalex.org/W2360759360"],"abstract_inverted_index":{"Weakly-supervised":[0],"semantic":[1],"segmentation":[2,8],"(WSSS),":[3],"which":[4],"aims":[5],"to":[6,110],"train":[7],"models":[9],"solely":[10],"using":[11,27],"image-level":[12,32,93],"labels,":[13],"has":[14],"achieved":[15],"significant":[16],"attention.":[17],"Existing":[18],"methods":[19],"primarily":[20],"focus":[21],"on":[22],"generating":[23,82],"high-quality":[24,106],"pseudo":[25,38],"labels":[26,39,94],"available":[28,46,90,143],"images":[29,84,91],"and":[30,92],"their":[31],"labels.":[33],"However,":[34],"the":[35,43,89,98,112,117,123,140,148],"quality":[36],"of":[37,45,119,142,150],"degrades":[40],"significantly":[41],"when":[42,139],"size":[44],"dataset":[47],"is":[48,136,145],"limited.":[49],"Thus,":[50],"in":[51],"this":[52,56],"paper,":[53],"we":[54,102],"tackle":[55],"problem":[57],"from":[58],"a":[59,64,105],"different":[60],"view":[61],"by":[62,81,116],"introducing":[63],"novel":[65],"approach":[66,128],"called":[67],"Image":[68],"Augmentation":[69],"with":[70],"Controlled":[71],"Diffusion":[72],"(IACD).":[73],"This":[74,134],"framework":[75],"effectively":[76],"augments":[77],"existing":[78,131],"labeled":[79],"datasets":[80],"diverse":[83],"through":[85],"controlled":[86],"diffusion,":[87],"where":[88],"are":[95],"served":[96],"as":[97],"controlling":[99],"information.":[100],"Moreover,":[101],"also":[103],"propose":[104],"image":[107],"selection":[108],"strategy":[109],"mitigate":[111],"potential":[113],"noise":[114],"introduced":[115],"randomness":[118],"diffusion":[120],"models.":[121],"In":[122],"experiments,":[124],"our":[125,151],"proposed":[126],"IACD":[127],"clearly":[129],"surpasses":[130],"state-of-the-art":[132],"methods.":[133],"effect":[135],"more":[137],"obvious":[138],"amount":[141],"data":[144],"small,":[146],"demonstrating":[147],"effectiveness":[149],"method.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":8}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2024-03-19T00:00:00"}