{"id":"https://openalex.org/W4285604202","doi":"https://doi.org/10.24963/ijcai.2022/193","title":"Iterative Few-shot Semantic Segmentation from Image Label Text","display_name":"Iterative Few-shot Semantic Segmentation from Image Label Text","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285604202","doi":"https://doi.org/10.24963/ijcai.2022/193"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/193","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/193","pdf_url":"https://www.ijcai.org/proceedings/2022/0193.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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 Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0193.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101892838","display_name":"Haohan Wang","orcid":"https://orcid.org/0000-0003-3451-6884"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haohan Wang","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School","Tsinghua Shenzhen International Graduate School, Tsinghua University","Shenzhen International Graduate School, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School","institution_ids":["https://openalex.org/I4210114105"]},{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100322345","display_name":"Liang Liu","orcid":"https://orcid.org/0000-0001-9491-8821"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Liu","raw_affiliation_strings":["Tencent","Tencent Youtu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091407315","display_name":"Wuhao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wuhao Zhang","raw_affiliation_strings":["Tencent","Tencent Youtu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021861529","display_name":"Jiangning Zhang","orcid":"https://orcid.org/0000-0001-8891-6766"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangning Zhang","raw_affiliation_strings":["Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075598739","display_name":"Zhenye Gan","orcid":"https://orcid.org/0000-0002-2431-1159"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenye Gan","raw_affiliation_strings":["Tencent","Tencent Youtu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028731909","display_name":"Yabiao Wang","orcid":"https://orcid.org/0000-0002-6592-8411"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yabiao Wang","raw_affiliation_strings":["Tencent","Tencent Youtu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chengjie Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengjie Wang","raw_affiliation_strings":["Tencent","Tencent Youtu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028229824","display_name":"Haoqian Wang","orcid":"https://orcid.org/0000-0003-2792-8469"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoqian Wang","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School","Tsinghua Shenzhen International Graduate School, Tsinghua University","Tencent Youtu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School","institution_ids":["https://openalex.org/I4210114105"]},{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tencent Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1385","last_page":"1392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9993000030517578,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9970999956130981,"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/pascal","display_name":"Pascal (unit)","score":0.8465744853019714},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8352577686309814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7156844735145569},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6993314027786255},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6747352480888367},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5468974113464355},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5141692161560059},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4957602918148041},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.47906240820884705},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4712928831577301},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.46985164284706116},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4540345370769501},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.43154606223106384},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4260457158088684},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3376007676124573},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3225785195827484},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.08900579810142517},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06408423185348511}],"concepts":[{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.8465744853019714},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8352577686309814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7156844735145569},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6993314027786255},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6747352480888367},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5468974113464355},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5141692161560059},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4957602918148041},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.47906240820884705},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4712928831577301},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46985164284706116},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4540345370769501},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43154606223106384},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4260457158088684},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3376007676124573},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3225785195827484},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.08900579810142517},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06408423185348511},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2022/193","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/193","pdf_url":"https://www.ijcai.org/proceedings/2022/0193.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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 Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2303.05646","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.05646","pdf_url":"https://arxiv.org/pdf/2303.05646","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/193","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/193","pdf_url":"https://www.ijcai.org/proceedings/2022/0193.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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 Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.550000011920929,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G4958032829","display_name":"\u5bbd\u89c6\u573a\u5c42\u6790\u8ba1\u7b97\u6210\u50cf\u7406\u8bba\u4e0e\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61831014","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285604202.pdf","grobid_xml":"https://content.openalex.org/works/W4285604202.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W2194775991","https://openalex.org/W2962858109","https://openalex.org/W2963078159","https://openalex.org/W2963599420","https://openalex.org/W2971113548","https://openalex.org/W2990230185","https://openalex.org/W2997490332","https://openalex.org/W3046971235","https://openalex.org/W3108189450","https://openalex.org/W3149878926","https://openalex.org/W3166396011","https://openalex.org/W3167453437","https://openalex.org/W3167559252","https://openalex.org/W3169024950","https://openalex.org/W3176065502","https://openalex.org/W3190736146","https://openalex.org/W3203637842","https://openalex.org/W3204077273","https://openalex.org/W3208004344","https://openalex.org/W3210769859","https://openalex.org/W3217193091","https://openalex.org/W4214660208","https://openalex.org/W4226058394","https://openalex.org/W4226452378","https://openalex.org/W4287162024","https://openalex.org/W4386790226"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2069133146","https://openalex.org/W2359774528","https://openalex.org/W4298312966"],"abstract_inverted_index":{"Few-shot":[0],"semantic":[1],"segmentation":[2],"aims":[3],"to":[4,6,54,112],"learn":[5],"segment":[7],"unseen":[8],"class":[9],"objects":[10],"with":[11,59],"the":[12,25,44,60,63,74,96,125,128],"guidance":[13],"of":[14,28,62,77],"only":[15,43,94],"a":[16,37,51,102],"few":[17],"support":[18,29,78],"images.":[19,30,81],"Most":[20],"previous":[21],"methods":[22],"rely":[23],"on":[24,36,84],"pixel-level":[26],"label":[27],"In":[31],"this":[32],"paper,":[33],"we":[34],"focus":[35],"more":[38],"challenging":[39],"setting,":[40],"in":[41,127],"which":[42],"image-level":[45],"labels":[46],"are":[47],"available.":[48],"We":[49],"propose":[50],"general":[52],"framework":[53],"firstly":[55],"generate":[56],"coarse":[57],"masks":[58],"help":[61],"powerful":[64],"vision-language":[65],"model":[66],"CLIP,":[67],"and":[68,71,79,86,130],"then":[69],"iteratively":[70],"mutually":[72],"refine":[73],"mask":[75],"predictions":[76],"query":[80],"Extensive":[82],"experiments":[83],"PASCAL-5i":[85],"COCO-20i":[87],"datasets":[88],"demonstrate":[89],"that":[90],"our":[91,117],"method":[92,118],"not":[93],"outperforms":[95],"state-of-the-art":[97],"weakly":[98],"supervised":[99,114],"approaches":[100],"by":[101],"significant":[103],"margin,":[104],"but":[105],"also":[106],"achieves":[107],"comparable":[108],"or":[109],"better":[110],"results":[111],"recent":[113],"methods.":[115],"Moreover,":[116],"owns":[119],"an":[120],"excellent":[121],"generalization":[122],"ability":[123],"for":[124],"images":[126],"wild":[129],"uncommon":[131],"classes.":[132],"Code":[133],"will":[134],"be":[135],"available":[136],"at":[137],"https://github.com/Whileherham/IMR-HSNet.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}