{"id":"https://openalex.org/W4393305255","doi":"https://doi.org/10.1109/tcsvt.2024.3383238","title":"Attention-Based Layer Fusion and Token Masking for Weakly Supervised Semantic Segmentation","display_name":"Attention-Based Layer Fusion and Token Masking for Weakly Supervised Semantic Segmentation","publication_year":2024,"publication_date":"2024-03-29","ids":{"openalex":"https://openalex.org/W4393305255","doi":"https://doi.org/10.1109/tcsvt.2024.3383238"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3383238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3383238","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5100388126","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0002-2028-048X"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu, China","Department of Computer Science, Sichuan University, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]},{"raw_affiliation_string":"Department of Computer Science, Sichuan University, China","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102734775","display_name":"Xiaotian Zhu","orcid":"https://orcid.org/0009-0000-9218-9864"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaotian Zhu","raw_affiliation_strings":["National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu, China","Department of Computer Science, Sichuan University, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24185976"]},{"raw_affiliation_string":"Department of Computer Science, Sichuan University, China","institution_ids":["https://openalex.org/I24185976"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100388126"],"corresponding_institution_ids":["https://openalex.org/I24185976"],"apc_list":null,"apc_paid":null,"fwci":1.0477,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.77818576,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"34","issue":"9","first_page":"7912","last_page":"7921"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9483000040054321,"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"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9483000040054321,"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/computer-science","display_name":"Computer science","score":0.7086386680603027},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6517854928970337},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.646324634552002},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.580143928527832},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5614038705825806},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5090784430503845},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4914013147354126},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44961023330688477},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41539067029953003},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3485279679298401},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1293318271636963},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06294459104537964}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7086386680603027},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6517854928970337},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.646324634552002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.580143928527832},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5614038705825806},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5090784430503845},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4914013147354126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44961023330688477},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41539067029953003},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3485279679298401},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1293318271636963},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06294459104537964},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3383238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3383238","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2050159143","https://openalex.org/W2108598243","https://openalex.org/W2144794286","https://openalex.org/W2295107390","https://openalex.org/W2306289963","https://openalex.org/W2558580397","https://openalex.org/W2600144439","https://openalex.org/W2798376494","https://openalex.org/W2799124825","https://openalex.org/W2962758679","https://openalex.org/W2962867364","https://openalex.org/W2964274719","https://openalex.org/W2982093251","https://openalex.org/W2997169099","https://openalex.org/W3034930876","https://openalex.org/W3107653507","https://openalex.org/W3142837074","https://openalex.org/W3166286626","https://openalex.org/W3173957243","https://openalex.org/W3177958285","https://openalex.org/W3203036314","https://openalex.org/W3203879378","https://openalex.org/W4226158211","https://openalex.org/W4312509967","https://openalex.org/W4312596526","https://openalex.org/W4312680544","https://openalex.org/W4312709262","https://openalex.org/W4312954872","https://openalex.org/W4313052647","https://openalex.org/W4313153210","https://openalex.org/W4315783894","https://openalex.org/W4383112609","https://openalex.org/W4386066092","https://openalex.org/W4386071798","https://openalex.org/W4386071966","https://openalex.org/W4386083104","https://openalex.org/W4386113282","https://openalex.org/W4391697061","https://openalex.org/W6753200639","https://openalex.org/W6788135285","https://openalex.org/W6791353385","https://openalex.org/W6841554388","https://openalex.org/W6851134139"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W4307309205","https://openalex.org/W4288261899","https://openalex.org/W2997152889","https://openalex.org/W4387768015","https://openalex.org/W4285141722"],"abstract_inverted_index":{"Weakly":[0],"Supervised":[1],"Semantic":[2],"Segmentation":[3],"(WSSS)":[4],"has":[5,46],"received":[6],"increasing":[7],"attentions":[8],"recently,":[9],"which":[10,78,145,173],"leverages":[11],"only":[12],"limited":[13,29],"supervision":[14],"to":[15,26,67,108,148,159],"train":[16],"the":[17,28,60,72,81,90,110,135],"segmentation":[18],"networks.":[19],"Meanwhile,":[20],"Transformer":[21,50],"utilizes":[22],"multi-head":[23],"attention":[24,136],"mechanism":[25],"overcome":[27],"receptive":[30],"fields":[31],"of":[32,43,54,83,138],"convolution":[33],"neural":[34],"networks":[35],"(CNN).":[36],"As":[37],"a":[38,40,117,125,150],"result,":[39],"large":[41],"amount":[42],"WSSS":[44],"work":[45],"been":[47,167],"built":[48],"upon":[49],"architecture.":[51],"However,":[52],"most":[53],"them":[55],"overlook":[56],"over-smoothing":[57],"issue":[58],"(i.e.":[59],"patch":[61],"tokens":[62],"in":[63,88,141,172],"deep":[64],"layers":[65,140],"tend":[66],"be":[68],"similar,":[69],"indicating":[70],"that":[71],"learned":[73],"information":[74,137],"is":[75,106],"nearly":[76],"identical),":[77],"will":[79],"affect":[80],"accuracy":[82],"Class":[84,127],"Activation":[85],"Map":[86],"(CAM)":[87],"representing":[89],"pixel":[91],"level":[92],"semantic":[93,162],"information.":[94,163],"In":[95],"this":[96],"paper,":[97],"an":[98,142],"Attention-based":[99],"Layer":[100,119],"Fusion":[101],"scheme":[102],"with":[103],"Token":[104,128],"Masking":[105],"proposed":[107],"address":[109],"above":[111],"issue.":[112],"The":[113,132,154],"core":[114],"modules":[115],"include":[116],"Weighted":[118],"Attention":[120],"Aggregation":[121],"(WLA)":[122],"module":[123],"and":[124],"Random-Masked":[126],"Refinement":[129],"(RMTR)":[130],"module.":[131],"former":[133],"integrates":[134],"different":[139],"adaptive":[143],"way,":[144],"refines":[146],"CAM":[147],"obtain":[149],"refined":[151],"object":[152],"contour.":[153],"latter":[155],"introduces":[156],"random":[157],"masks":[158],"aggregate":[160],"higher-level":[161],"Extensive":[164],"experiments":[165],"have":[166],"conducted":[168],"on":[169],"public":[170],"datasets,":[171],"our":[174],"network":[175],"manifests":[176],"superior":[177],"performances":[178],"than":[179],"other":[180],"state-of-the-arts":[181],"methods.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}