{"id":"https://openalex.org/W7127270030","doi":"https://doi.org/10.1109/rivf68649.2025.11365118","title":"From Discriminative Regions to Complete Masks: CAM-SAM Fusion for Weakly Supervised Semantic Segmentation","display_name":"From Discriminative Regions to Complete Masks: CAM-SAM Fusion for Weakly Supervised Semantic Segmentation","publication_year":2025,"publication_date":"2025-12-18","ids":{"openalex":"https://openalex.org/W7127270030","doi":"https://doi.org/10.1109/rivf68649.2025.11365118"},"language":null,"primary_location":{"id":"doi:10.1109/rivf68649.2025.11365118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf68649.2025.11365118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 RIVF International Conference on Computing and Communication Technologies (RIVF)","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/A5124965996","display_name":"Yen Nhi Huynh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yen Nhi Huynh","raw_affiliation_strings":["University of Information Technology,Ho Chi Minh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124932289","display_name":"Tr\u1ea7n Quang Huy Nguy\u1ec5n","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tran Khuong An Nguyen","raw_affiliation_strings":["University of Information Technology,Ho Chi Minh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124875536","display_name":"Tien-Dung Mai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tien-Dung Mai","raw_affiliation_strings":["University of Information Technology,Ho Chi Minh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62318167,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"108","last_page":"113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.925599992275238,"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":0.925599992275238,"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":0.021199999377131462,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.008899999782443047,"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/segmentation","display_name":"Segmentation","score":0.8310999870300293},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8277999758720398},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.7348999977111816},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5525000095367432},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5432000160217285},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.47540000081062317},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.47040000557899475}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8310999870300293},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8277999758720398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7400000095367432},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.7348999977111816},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7102000117301941},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5525000095367432},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5432000160217285},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.47540000081062317},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.47040000557899475},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4291999936103821},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4219000041484833},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.35010001063346863},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3479999899864197},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.34299999475479126},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31679999828338623},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30309998989105225},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.27399998903274536},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rivf68649.2025.11365118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf68649.2025.11365118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 RIVF International Conference on Computing and Communication Technologies (RIVF)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7894801497459412,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W611457968","https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2144794286","https://openalex.org/W2295107390","https://openalex.org/W2337429362","https://openalex.org/W2552414813","https://openalex.org/W2600144439","https://openalex.org/W2962758679","https://openalex.org/W3034930876","https://openalex.org/W3138516171","https://openalex.org/W3183732083","https://openalex.org/W4220950530","https://openalex.org/W4312815172","https://openalex.org/W4386083104","https://openalex.org/W4390874575","https://openalex.org/W4399766673","https://openalex.org/W4402727341","https://openalex.org/W4402727630","https://openalex.org/W4405104655","https://openalex.org/W4405114436","https://openalex.org/W4413145032"],"related_works":[],"abstract_inverted_index":{"Semantic":[0,15],"segmentation":[1,127,145],"requires":[2],"costly":[3],"pixel-level":[4],"annotations,":[5],"limiting":[6],"the":[7,52,58,64,135],"scalability":[8],"of":[9,55,63,137],"fully":[10],"supervised":[11],"models.":[12],"Weakly":[13],"Supervised":[14],"Segmentation":[16],"(WSSS)":[17],"reduces":[18],"this":[19],"burden":[20],"using":[21],"image-level":[22],"labels,":[23],"but":[24],"existing":[25],"methods":[26],"based":[27],"on":[28,104],"Class":[29],"Activation":[30],"Maps":[31],"(CAM)":[32],"often":[33],"capture":[34],"only":[35],"small":[36],"discriminative":[37],"object":[38],"regions,":[39],"yielding":[40],"incomplete":[41],"pseudo":[42,101],"masks.":[43],"We":[44],"introduce":[45],"a":[46,87],"CAM-SAM":[47],"fusion":[48],"framework":[49],"that":[50,91,113],"combines":[51],"semantic":[53],"cues":[54],"CAM":[56,77,94],"with":[57,146],"strong":[59],"boundary":[60],"localization":[61],"capabilities":[62],"Segment":[65],"Anything":[66],"Model":[67],"(SAM).":[68],"Specifically,":[69],"we":[70],"propose":[71],"Semantic-Aware":[72],"Prompting":[73],"(SAP),":[74],"where":[75],"highresponse":[76],"peaks":[78],"to":[79,98,123],"guide":[80],"SAM":[81,96],"in":[82,126],"generating":[83],"detailed":[84],"masks,":[85,121],"and":[86,95,108,118],"Mask":[88],"Fusion":[89],"Algorithm":[90],"intelligently":[92],"integrates":[93],"outputs":[97],"produce":[99],"reliable":[100],"labels.":[102],"Evaluations":[103],"PASCAL":[105],"VOC":[106],"2012":[107],"MS":[109],"COCO":[110],"2014":[111],"show":[112],"our":[114],"method":[115],"produces":[116],"sharper":[117],"more":[119],"complete":[120],"leading":[122],"significant":[124],"improvements":[125],"accuracy":[128],"over":[129],"CAM-only":[130],"baselines.":[131],"These":[132],"results":[133],"highlight":[134],"effectiveness":[136],"integrating":[138],"foundation":[139],"models":[140],"into":[141],"WSSS":[142],"for":[143],"high-quality":[144],"minimal":[147],"supervision.":[148]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-04T00:00:00"}