{"id":"https://openalex.org/W4392781114","doi":"https://doi.org/10.48550/arxiv.2403.07630","title":"Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentation","display_name":"Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentation","publication_year":2024,"publication_date":"2024-03-12","ids":{"openalex":"https://openalex.org/W4392781114","doi":"https://doi.org/10.48550/arxiv.2403.07630"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2403.07630","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.07630","pdf_url":"https://arxiv.org/pdf/2403.07630","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.07630","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007640861","display_name":"Feilong Tang","orcid":"https://orcid.org/0000-0002-1384-198X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tang, Feilong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015118469","display_name":"Zhongxing Xu","orcid":"https://orcid.org/0000-0003-3815-7647"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Zhongxing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113395517","display_name":"Zhaojun Qu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qu, Zhaojun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083198458","display_name":"Feng Wei","orcid":"https://orcid.org/0000-0002-2900-6321"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072600418","display_name":"Xingjian Jiang","orcid":"https://orcid.org/0000-0003-4656-0532"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Xingjian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005014252","display_name":"Zongyuan Ge","orcid":"https://orcid.org/0000-0002-5880-8673"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ge, Zongyuan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5007640861"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.982699990272522,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.982699990272522,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9585000276565552,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9358999729156494,"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":0.7174466848373413},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6811537146568298},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5733240842819214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5490541458129883},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4910554885864258},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3521965742111206},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.16167938709259033}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7174466848373413},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6811537146568298},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5733240842819214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5490541458129883},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4910554885864258},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3521965742111206},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.16167938709259033},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2403.07630","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.07630","pdf_url":"https://arxiv.org/pdf/2403.07630","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.07630","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.07630","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.07630","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.07630","pdf_url":"https://arxiv.org/pdf/2403.07630","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392781114.pdf","grobid_xml":"https://content.openalex.org/works/W4392781114.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347","https://openalex.org/W4210805261"],"abstract_inverted_index":{"Recent":[0],"weakly":[1],"supervised":[2],"semantic":[3,103,119,147],"segmentation":[4],"(WSSS)":[5],"methods":[6,200],"strive":[7],"to":[8,12,40,55,80,87,97,121,131,145,157,176],"incorporate":[9],"contextual":[10,68],"knowledge":[11,28,82],"improve":[13],"the":[14,27,35,38,89,95,143,146],"completeness":[15],"of":[16,37,62,127,149],"class":[17],"activation":[18],"maps":[19],"(CAM).":[20],"In":[21,168],"this":[22,81,107,128],"work,":[23],"we":[24,50,85,109],"argue":[25],"that":[26,67,195],"bias":[29,96],"between":[30],"instances":[31],"and":[32,58,74,181,190,201],"contexts":[33],"affects":[34],"capability":[36],"prototype":[39,47,53,90,159],"sufficiently":[41],"understand":[42],"instance":[43,123,162],"semantics.":[44],"Inspired":[45],"by":[46,93],"learning":[48],"theory,":[49],"propose":[51,86],"leveraging":[52],"awareness":[54],"capture":[56,99,133],"diverse":[57],"fine-grained":[59],"feature":[60,154,163],"attributes":[61,148],"instances.":[63,151],"The":[64,125,205],"hypothesis":[65],"is":[66,130,174,207],"prototypes":[69],"might":[70],"erroneously":[71],"activate":[72],"similar":[73],"frequently":[75],"co-occurring":[76],"object":[77,104,137],"categories":[78],"due":[79],"bias.":[83],"Therefore,":[84],"enhance":[88],"representation":[91],"ability":[92],"mitigating":[94],"better":[98],"spatial":[100],"coverage":[101],"in":[102,136],"regions.":[105],"With":[106],"goal,":[108],"present":[110],"a":[111,170],"Context":[112],"Prototype-Aware":[113],"Learning":[114],"(CPAL)":[115],"strategy,":[116],"which":[117],"leverages":[118],"context":[120],"enrich":[122],"comprehension.":[124],"core":[126],"method":[129],"accurately":[132],"intra-class":[134],"variations":[135],"features":[138],"through":[139],"context-aware":[140],"prototypes,":[141],"facilitating":[142],"adaptation":[144],"various":[150],"We":[152],"design":[153],"distribution":[155],"alignment":[156],"optimize":[158],"awareness,":[160],"aligning":[161],"distributions":[164],"with":[165],"dense":[166],"features.":[167],"addition,":[169],"unified":[171],"training":[172],"framework":[173],"proposed":[175],"combine":[177],"label-guided":[178],"classification":[179],"supervision":[180],"prototypes-guided":[182],"self-supervision.":[183],"Experimental":[184],"results":[185],"on":[186],"PASCAL":[187],"VOC":[188],"2012":[189],"MS":[191],"COCO":[192],"2014":[193],"show":[194],"CPAL":[196],"significantly":[197],"improves":[198],"off-the-shelf":[199],"achieves":[202],"state-of-the-art":[203],"performance.":[204],"project":[206],"available":[208],"at":[209],"https://github.com/Barrett-python/CPAL.":[210]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}