{"id":"https://openalex.org/W4304091443","doi":"https://doi.org/10.1145/3503161.3548201","title":"Boat in the Sky: Background Decoupling and Object-aware Pooling for Weakly Supervised Semantic Segmentation","display_name":"Boat in the Sky: Background Decoupling and Object-aware Pooling for Weakly Supervised Semantic Segmentation","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304091443","doi":"https://doi.org/10.1145/3503161.3548201"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548201","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548201","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5101531218","display_name":"Jianjun Xu","orcid":"https://orcid.org/0000-0001-6398-3364"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianjun Xu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078162380","display_name":"Hongtao Xie","orcid":"https://orcid.org/0000-0002-6249-5315"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongtao Xie","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086466927","display_name":"Xu Hai","orcid":"https://orcid.org/0000-0003-4644-9033"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Xu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427468","display_name":"Yuxin Wang","orcid":"https://orcid.org/0000-0002-0228-6220"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046158385","display_name":"Sun-Ao Liu","orcid":"https://orcid.org/0009-0002-7913-0483"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun-ao Liu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046305086","display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101531218"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.7791,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.80721517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5783","last_page":"5792"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10627","display_name":"Advanced Image and Video Retrieval 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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9972000122070312,"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":0.7450206279754639},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.7343164086341858},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.7025969624519348},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6668888330459595},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5429139137268066},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.4816542863845825},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4527873396873474},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.44246453046798706},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4252024292945862},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.4203149378299713},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38006553053855896},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2852247655391693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7450206279754639},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.7343164086341858},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7025969624519348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6668888330459595},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5429139137268066},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.4816542863845825},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4527873396873474},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.44246453046798706},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4252024292945862},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.4203149378299713},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38006553053855896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2852247655391693},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548201","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548201","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7799999713897705,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1538422756","https://openalex.org/W1861492603","https://openalex.org/W1903029394","https://openalex.org/W2133515615","https://openalex.org/W2144794286","https://openalex.org/W2194775991","https://openalex.org/W2295107390","https://openalex.org/W2306289963","https://openalex.org/W2412782625","https://openalex.org/W2585747585","https://openalex.org/W2600144439","https://openalex.org/W2605214291","https://openalex.org/W2799124825","https://openalex.org/W2903703378","https://openalex.org/W2962758679","https://openalex.org/W2962867364","https://openalex.org/W2963045696","https://openalex.org/W2963198662","https://openalex.org/W2963606198","https://openalex.org/W2964309882","https://openalex.org/W2980189057","https://openalex.org/W2982093251","https://openalex.org/W2992308087","https://openalex.org/W2997851315","https://openalex.org/W3005164579","https://openalex.org/W3032908737","https://openalex.org/W3034333089","https://openalex.org/W3034930876","https://openalex.org/W3035679705","https://openalex.org/W3035872583","https://openalex.org/W3099088591","https://openalex.org/W3102659010","https://openalex.org/W3107653507","https://openalex.org/W3164772195","https://openalex.org/W3166286626","https://openalex.org/W3169761117","https://openalex.org/W3175156984","https://openalex.org/W3176760243","https://openalex.org/W3180638445","https://openalex.org/W3183732083","https://openalex.org/W3196990496","https://openalex.org/W3203879378","https://openalex.org/W4205260486","https://openalex.org/W4283821214"],"related_works":["https://openalex.org/W4376620596","https://openalex.org/W3177249605","https://openalex.org/W2534152068","https://openalex.org/W3138508047","https://openalex.org/W1972515067","https://openalex.org/W1689909837","https://openalex.org/W4293054914","https://openalex.org/W4298525700","https://openalex.org/W2953362004","https://openalex.org/W2549121492"],"abstract_inverted_index":{"Previous":[0],"image-level":[1],"weakly-supervised":[2],"semantic":[3,67,91],"segmentation":[4],"methods":[5],"based":[6],"on":[7,17,171],"Class":[8],"Activation":[9],"Map":[10],"(CAM)":[11],"have":[12],"two":[13],"limitations:":[14],"1)":[15],"focusing":[16],"partial":[18],"discriminative":[19],"foreground":[20],"regions":[21],"and":[22,39,43,68,77,123,151,177],"2)":[23],"containing":[24],"undesirable":[25],"background.":[26],"The":[27,139],"above":[28],"issues":[29],"are":[30],"attributed":[31],"to":[32,64,88,115,135,146],"the":[33,37,44,50,66,72,90,95,101,117,120,124,154,161,173],"spurious":[34],"correlations":[35],"between":[36,119],"object":[38,78,121],"background":[40,75,82],"(semantic":[41],"ambiguity)":[42],"insufficient":[45],"spatial":[46,69,137,149],"perception":[47],"ability":[48],"of":[49,74,97,156,163],"classification":[51],"network":[52],"(spatial":[53],"ambiguity).":[54],"In":[55],"this":[56],"work,":[57],"we":[58],"propose":[59],"a":[60,81,110,128,142],"novel":[61],"self-supervised":[62],"framework":[63],"mitigate":[65],"ambiguity":[70,92],"from":[71,100],"perspectives":[73],"bias":[76],"perception.":[79],"First,":[80],"decoupling":[83],"mechanism":[84],"(BDM)":[85],"is":[86,113,133],"proposed":[87],"handle":[89],"by":[93,166],"regularizing":[94],"consistency":[96],"predicted":[98],"CAMs":[99],"samples":[102],"with":[103],"identical":[104],"foregrounds":[105],"but":[106],"different":[107],"backgrounds.":[108],"Thus,":[109],"decoupled":[111],"relationship":[112],"constructed":[114],"reduce":[116],"dependence":[118],"instance":[122],"scene":[125],"information.":[126],"Second,":[127],"global":[129],"object-aware":[130,144],"pooling":[131],"(GOP)":[132],"introduced":[134],"alleviate":[136],"ambiguity.":[138],"GOP":[140],"utilizes":[141],"learnable":[143],"map":[145],"dynamically":[147],"aggregate":[148],"information":[150],"further":[152],"improve":[153],"performance":[155],"CAMs.":[157],"Extensive":[158],"experiments":[159],"demonstrate":[160],"effectiveness":[162],"our":[164],"method":[165],"achieving":[167],"new":[168],"state-of-the-art":[169],"results":[170],"both":[172],"Pascal":[174],"VOC":[175],"2012":[176],"MS":[178],"COCO":[179],"2014":[180],"datasets.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}