{"id":"https://openalex.org/W3204311811","doi":"https://doi.org/10.1109/tpami.2021.3114342","title":"A Holistically-Guided Decoder for Deep Representation Learning With Applications to Semantic Segmentation and Object Detection","display_name":"A Holistically-Guided Decoder for Deep Representation Learning With Applications to Semantic Segmentation and Object Detection","publication_year":2021,"publication_date":"2021-09-29","ids":{"openalex":"https://openalex.org/W3204311811","doi":"https://doi.org/10.1109/tpami.2021.3114342","mag":"3204311811","pmid":"https://pubmed.ncbi.nlm.nih.gov/34587003"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2021.3114342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3114342","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100361599","display_name":"Jianbo Liu","orcid":"https://orcid.org/0000-0003-4392-1056"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jianbo Liu","raw_affiliation_strings":["Department of Electrical Engineering, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-4392-1056","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056327997","display_name":"Junjun He","orcid":"https://orcid.org/0000-0002-1813-1784"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjun He","raw_affiliation_strings":["SenseTime Research, shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, shanghai, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007211501","display_name":"Yuanjie Zheng","orcid":"https://orcid.org/0000-0002-5786-2491"},"institutions":[{"id":"https://openalex.org/I28006308","display_name":"Shandong Normal University","ror":"https://ror.org/01wy3h363","country_code":"CN","type":"education","lineage":["https://openalex.org/I28006308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanjie Zheng","raw_affiliation_strings":["School of Information Science and Engineering, Shandong Normal University, Jinan, Shandong, China"],"raw_orcid":"https://orcid.org/0000-0002-5786-2491","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Shandong Normal University, Jinan, Shandong, China","institution_ids":["https://openalex.org/I28006308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101696728","display_name":"Shuai Yi","orcid":"https://orcid.org/0000-0002-1253-6633"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Yi","raw_affiliation_strings":["SenseTime Research, shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, shanghai, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100444820","display_name":"Xiaogang Wang","orcid":"https://orcid.org/0000-0002-7929-5889"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaogang Wang","raw_affiliation_strings":["Department of Electrical Engineering, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100732450","display_name":"Hongsheng Li","orcid":"https://orcid.org/0000-0002-2664-7975"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hongsheng Li","raw_affiliation_strings":["Department of Electrical Engineering, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-2664-7975","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7537,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.73421441,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"45","issue":"10","first_page":"11390","last_page":"11406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.8282354474067688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6475755572319031},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6344389319419861},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6296133995056152},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5432426333427429},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.5051916241645813},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5034794211387634},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4824838936328888},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.45434898138046265},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43712201714515686},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.42861640453338623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8282354474067688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6475755572319031},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6344389319419861},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6296133995056152},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5432426333427429},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.5051916241645813},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5034794211387634},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4824838936328888},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.45434898138046265},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43712201714515686},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.42861640453338623},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2021.3114342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3114342","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:34587003","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34587003","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1745334888","https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W1910657905","https://openalex.org/W2031489346","https://openalex.org/W2117539524","https://openalex.org/W2124592697","https://openalex.org/W2125215748","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2412782625","https://openalex.org/W2560023338","https://openalex.org/W2563705555","https://openalex.org/W2565639579","https://openalex.org/W2630837129","https://openalex.org/W2737258237","https://openalex.org/W2752782242","https://openalex.org/W2768489488","https://openalex.org/W2780664485","https://openalex.org/W2890782586","https://openalex.org/W2895340641","https://openalex.org/W2895420332","https://openalex.org/W2921781974","https://openalex.org/W2924464923","https://openalex.org/W2952147788","https://openalex.org/W2955058313","https://openalex.org/W2955813853","https://openalex.org/W2962721361","https://openalex.org/W2962850830","https://openalex.org/W2963108253","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963381188","https://openalex.org/W2963563573","https://openalex.org/W2963727650","https://openalex.org/W2963857746","https://openalex.org/W2964309882","https://openalex.org/W2964444661","https://openalex.org/W2965391153","https://openalex.org/W2970575838","https://openalex.org/W2981899103","https://openalex.org/W2985459778","https://openalex.org/W2987322772","https://openalex.org/W2990775046","https://openalex.org/W2991062542","https://openalex.org/W2991471181","https://openalex.org/W3014641072","https://openalex.org/W3034971973","https://openalex.org/W3035339581","https://openalex.org/W3035526186","https://openalex.org/W3040304705","https://openalex.org/W3108986454","https://openalex.org/W3110440461","https://openalex.org/W4234117503","https://openalex.org/W4288325606","https://openalex.org/W6604653223","https://openalex.org/W6620707391","https://openalex.org/W6639102338","https://openalex.org/W6639780620","https://openalex.org/W6639824700","https://openalex.org/W6730411969","https://openalex.org/W6739696289","https://openalex.org/W6748481559","https://openalex.org/W6751325469","https://openalex.org/W6754879843","https://openalex.org/W6760897771","https://openalex.org/W6764322716","https://openalex.org/W6767109091","https://openalex.org/W6776080156"],"related_works":["https://openalex.org/W2493838176","https://openalex.org/W4297686120","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/W4313315626"],"abstract_inverted_index":{"Both":[0],"high-level":[1,21,177],"and":[2,68,75,105,167,178,198,203],"high-resolution":[3,17,38,59,147],"feature":[4,18,39,60,91,95,149],"representations":[5],"are":[6,55,124],"of":[7,117,174,220],"great":[8],"importance":[9],"in":[10,32],"various":[11],"visual":[12],"understanding":[13],"tasks.":[14],"To":[15,71],"acquire":[16],"maps":[19,92,150],"with":[20,128,217,251],"semantic":[22,47,109,122,196,225],"information,":[23],"one":[24,137],"common":[25],"strategy":[26],"is":[27,142,160],"to":[28,36,51,144],"adopt":[29],"dilated":[30],"convolutions":[31],"the":[33,43,58,73,85,99,106,115,129,146,152,156,176,182,186,192,235],"backbone":[34],"networks":[35],"extract":[37],"maps,":[40,61],"such":[41,62,97],"as":[42,98],"dilatedFCN-based":[44,130],"methods":[45,63,120,216],"for":[46,102,108,121,195,200,224],"segmentation.":[48,110,205],"However,":[49],"due":[50],"many":[52],"convolution":[53],"operations":[54],"conducted":[56],"on":[57,227],"have":[64],"large":[65],"computational":[66,222],"complexity":[67],"memory":[69],"consumption.":[70],"balance":[72],"performance":[74,213],"efficiency,":[76],"there":[77],"also":[78],"exist":[79],"encoder-decoder":[80,119],"structures":[81],"that":[82],"gradually":[83],"recover":[84],"spatial":[86],"information":[87],"by":[88],"combining":[89],"multi-level":[90],"from":[93,126,155,181],"a":[94],"encoder,":[96],"FPN":[100],"architecture":[101,194],"object":[103,201,248],"detection":[104,202,249],"U-Net":[107],"Although":[111],"being":[112],"more":[113],"efficient,":[114],"performances":[116],"existing":[118],"segmentation":[123,197,226],"far":[125],"comparable":[127,209],"methods.":[131],"In":[132],"this":[133],"paper,":[134],"we":[135,190],"propose":[136],"novel":[138,163],"holistically-guided":[139,188],"decoder":[140],"which":[141,171],"introduced":[143],"obtain":[145],"semantic-rich":[148],"via":[151,162],"multi-scale":[153],"features":[154,180],"encoder.":[157],"The":[158,206],"decoding":[159],"achieved":[161],"holistic":[164],"codeword":[165,168],"generation":[166],"assembly":[169],"operations,":[170],"take":[172],"advantages":[173],"both":[175],"low-level":[179],"encoder":[183],"features.":[184],"With":[185],"proposed":[187,236],"decoder,":[189],"implement":[191],"EfficientFCN":[193,207],"HGD-FPN":[199,237],"instance":[204],"achieves":[208,238],"or":[210],"even":[211],"better":[212],"than":[214],"state-of-the-art":[215],"only":[218],"1/3":[219],"their":[221],"costs":[223],"PASCAL":[228,230],"Context,":[229],"VOC,":[231],"ADE20K":[232],"datasets.":[233],"Meanwhile,":[234],"higher":[239],"mean":[240],"Average":[241],"Precision":[242],"(mAP)":[243],"when":[244],"integrated":[245],"into":[246],"several":[247],"frameworks":[250],"ResNet-50":[252],"encoding":[253],"backbones.":[254]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}