{"id":"https://openalex.org/W4402979689","doi":"https://doi.org/10.1109/icme57554.2024.10688161","title":"Memory-guided Network with Uncertainty-based Feature Augmentation for Few-shot Semantic Segmentation","display_name":"Memory-guided Network with Uncertainty-based Feature Augmentation for Few-shot Semantic Segmentation","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979689","doi":"https://doi.org/10.1109/icme57554.2024.10688161"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688161","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100707821","display_name":"Xinyue Chen","orcid":"https://orcid.org/0000-0003-0834-3967"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Xinyue Chen","raw_affiliation_strings":["King’s College London,Department of Informatics,London,UK"],"affiliations":[{"raw_affiliation_string":"King’s College London,Department of Informatics,London,UK","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101675323","display_name":"Miaojing Shi","orcid":"https://orcid.org/0000-0002-4933-0073"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miaojing Shi","raw_affiliation_strings":["Tongji University,College of Electronic and Information Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Tongji University,College of Electronic and Information Engineering,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100707821"],"corresponding_institution_ids":["https://openalex.org/I183935753"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1678583,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9873999953269958,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9873999953269958,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9833999872207642,"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":0.9815000295639038,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8010998964309692},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6929326057434082},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6921579837799072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6370102763175964},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.615145206451416},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.5650734901428223},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46461808681488037},{"id":"https://openalex.org/keywords/semantic-memory","display_name":"Semantic memory","score":0.4285346567630768},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40902137756347656},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.0708182156085968},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06544360518455505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8010998964309692},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6929326057434082},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6921579837799072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6370102763175964},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.615145206451416},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.5650734901428223},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46461808681488037},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.4285346567630768},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40902137756347656},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.0708182156085968},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06544360518455505},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688161","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2364155688","https://openalex.org/W2046522763","https://openalex.org/W2366916257","https://openalex.org/W2375847997","https://openalex.org/W2072836406","https://openalex.org/W2391772185","https://openalex.org/W2061641547","https://openalex.org/W4386420450","https://openalex.org/W2355099127","https://openalex.org/W2361892564"],"abstract_inverted_index":{"The":[0],"performance":[1,122,177],"of":[2,12,40,51,79,82,178,182],"supervised":[3],"semantic":[4,21],"segmentation":[5,22,39],"methods":[6,47],"highly":[7],"relies":[8],"on":[9,31,54,163],"the":[10,28,38,49,59,109,121,126,148,164,175,183],"availability":[11],"large-scale":[13],"training":[14,97,104,145],"data.":[15,45],"To":[16,67],"alleviate":[17],"this":[18,69],"dependence,":[19],"few-shot":[20],"(FSS)":[23],"is":[24],"introduced":[25],"to":[26,58,118,139],"leverage":[27],"model":[29,52],"trained":[30],"base":[32,63,94,113],"classes":[33,42,56,95],"with":[34,43,120,160],"sufficient":[35],"data":[36],"into":[37,156],"novel":[41,55,65,115],"few":[44],"FSS":[46,158],"face":[48],"challenge":[50],"generalization":[53],"due":[57],"distribution":[60,110],"shift":[61],"between":[62,112],"and":[64,105,114,154,169],"classes.":[66,116],"overcome":[68],"issue,":[70],"we":[71,131],"propose":[72],"a":[73,80],"class-shared":[74],"memory":[75,84,87],"(CSM)":[76],"module":[77,138],"consisting":[78],"set":[81],"learnable":[83],"vectors.":[85],"These":[86],"vectors":[88],"learn":[89],"elemental":[90],"object":[91],"patterns":[92],"from":[93,125],"during":[96,102,144],"whilst":[98],"re-encoding":[99],"query":[100,142],"features":[101,143],"both":[103],"inference,":[106],"thereby":[107],"improving":[108,147],"alignment":[111],"Furthermore,":[117],"cope":[119],"degradation":[123],"resulting":[124],"intra-class":[127],"variance":[128],"across":[129],"images,":[130],"introduce":[132],"an":[133],"uncertainty-based":[134],"feature":[135],"augmentation":[136],"(UFA)":[137],"produce":[140],"diverse":[141],"for":[146],"model\u2019s":[149],"robustness.":[150],"We":[151],"integrate":[152],"CSM":[153],"UFA":[155],"representative":[157],"works,":[159],"experimental":[161],"results":[162],"widely-used":[165],"PASCAL-5i":[168,172],"COCO-20