{"id":"https://openalex.org/W4400275685","doi":"https://doi.org/10.1109/tits.2024.3417813","title":"SDPT: Semantic-Aware Dimension-Pooling Transformer for Image Segmentation","display_name":"SDPT: Semantic-Aware Dimension-Pooling Transformer for Image Segmentation","publication_year":2024,"publication_date":"2024-07-03","ids":{"openalex":"https://openalex.org/W4400275685","doi":"https://doi.org/10.1109/tits.2024.3417813"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2024.3417813","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tits.2024.3417813","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Transportation Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tits.2024.3417813","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011193488","display_name":"Hu Cao","orcid":"https://orcid.org/0000-0001-8225-858X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Hu Cao","raw_affiliation_strings":["Chair of Robotics, Artificial Intelligence and Real-Time Systems, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8225-858X","affiliations":[{"raw_affiliation_string":"Chair of Robotics, Artificial Intelligence and Real-Time Systems, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323037","display_name":"Guang Chen","orcid":"https://orcid.org/0000-0002-7416-592X"},"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":"Guang Chen","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7416-592X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078109015","display_name":"Hengshuang Zhao","orcid":"https://orcid.org/0000-0001-8277-2706"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hengshuang Zhao","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Pokfulam, Hong Kong","Department of Computer Science, The University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-8277-2706","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Pokfulam, Hong Kong","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103215306","display_name":"Dongsheng Jiang","orcid":"https://orcid.org/0000-0002-7390-9173"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongsheng Jiang","raw_affiliation_strings":["Huawei Technologies, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7390-9173","affiliations":[{"raw_affiliation_string":"Huawei Technologies, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614065","display_name":"Xiaopeng Zhang","orcid":"https://orcid.org/0000-0001-6337-5748"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Zhang","raw_affiliation_strings":["Huawei Technologies, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6337-5748","affiliations":[{"raw_affiliation_string":"Huawei Technologies, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393506","display_name":"Qi Tian","orcid":"https://orcid.org/0000-0002-7252-5047"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["Huawei Technologies, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7252-5047","affiliations":[{"raw_affiliation_string":"Huawei Technologies, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063781430","display_name":"Alois Knoll","orcid":"https://orcid.org/0000-0003-4840-076X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alois Knoll","raw_affiliation_strings":["Chair of Robotics, Artificial Intelligence and Real-Time Systems, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4840-076X","affiliations":[{"raw_affiliation_string":"Chair of Robotics, Artificial Intelligence and Real-Time Systems, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5011193488"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":3.3331,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.93435059,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"25","issue":"11","first_page":"15934","last_page":"15946"},"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":0.9993000030517578,"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":0.9990000128746033,"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/pooling","display_name":"Pooling","score":0.769608736038208},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7073243260383606},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7004595994949341},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6074277758598328},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.573056697845459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45609036087989807},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4526228904724121},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37159594893455505},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32754606008529663}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.769608736038208},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7073243260383606},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7004595994949341},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6074277758598328},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.573056697845459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45609036087989807},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4526228904724121},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37159594893455505},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32754606008529663},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2024.3417813","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tits.2024.3417813","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Transportation Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tits.2024.3417813","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tits.2024.3417813","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Transportation Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1605215565","display_name":null,"funder_award_id":"62372329","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":false,"pdf":false},"content_urls":null,"referenced_works_count":84,"referenced_works":["https://openalex.org/W1585431621","https://openalex.org/W1849277567","https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2003099669","https://openalex.org/W2017745767","https://openalex.org/W2024168391","https://openalex.org/W2067191022","https://openalex.org/W2108598243","https://openalex.org/W2145023731","https://openalex.org/W2169099300","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2412782625","https://openalex.org/W2560023338","https://openalex.org/W2561196672","https://openalex.org/W2565639579","https://openalex.org/W2592939477","https://openalex.org/W2737258237","https://openalex.org/W2787091153","https://openalex.org/W2886934227","https://openalex.org/W2888347706","https://openalex.org/W2896014703","https://openalex.org/W2955058313","https://openalex.org/W2962721361","https://openalex.org/W2962914239","https://openalex.org/W2963091558","https://openalex.org/W2963150697","https://openalex.org/W2963727650","https://openalex.org/W2963857746","https://openalex.org/W2964217532","https://openalex.org/W2981689412","https://openalex.org/W3008115128","https://openalex.org/W3034502973","https://openalex.org/W3039515597","https://openalex.org/W3083765505","https://openalex.org/W3096609285","https://openalex.org/W3110908156","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3132455321","https://openalex.org/W3138516171","https://openalex.org/W3139633126","https://openalex.org/W3148302677","https://openalex.org/W3159637683","https://openalex.org/W3169865585","https://openalex.org/W3170279373","https://openalex.org/W3170841864","https://openalex.org/W3174972748","https://openalex.org/W3175515048","https://openalex.org/W3186077919","https://openalex.org/W3196904463","https://openalex.org/W4206491954","https://openalex.org/W4207077357","https://openalex.org/W4214520160","https://openalex.org/W4214893857","https://openalex.org/W4293680532","https://openalex.org/W4311166797","https://openalex.org/W4312422436","https://openalex.org/W4312443924","https://openalex.org/W4312726009","https://openalex.org/W4312785900","https://openalex.org/W4312815172","https://openalex.org/W4313160444","https://openalex.org/W4315777492","https://openalex.org/W4315884020","https://openalex.org/W4321232185","https://openalex.org/W4385245566","https://openalex.org/W4386076267","https://openalex.org/W4386179772","https://openalex.org/W4393159321","https://openalex.org/W6634966438","https://openalex.org/W6757817989","https://openalex.org/W6766978945","https://openalex.org/W6788135285","https://openalex.org/W6794345597","https://openalex.org/W6797399245","https://openalex.org/W6797790494","https://openalex.org/W6798837711","https://openalex.org/W6803650990","https://openalex.org/W6842806116","https://openalex.org/W6846529796","https://openalex.org/W6848963243"],"related_works":["https://openalex.org/W2095407248","https://openalex.org/W2393351060","https://openalex.org/W1997714924","https://openalex.org/W2129190845","https://openalex.org/W4389045637","https://openalex.org/W1994209155","https://openalex.org/W2076843925","https://openalex.org/W4384300015","https://openalex.org/W2054979592","https://openalex.org/W2100712766"],"abstract_inverted_index":{"Image":[0],"segmentation":[1],"plays":[2],"a":[3,13,37,98,108,124,146,155],"critical":[4],"role":[5],"in":[6,27,63,113],"autonomous":[7],"driving":[8],"by":[9],"providing":[10],"vehicles":[11],"with":[12,53,204],"detailed":[14],"and":[15,42,83,97,123,171,180],"accurate":[16],"understanding":[17],"of":[18,47,56],"their":[19,61],"surroundings.":[20],"Transformers":[21],"have":[22],"recently":[23],"shown":[24],"encouraging":[25],"results":[26],"image":[28],"segmentation.":[29],"However,":[30],"transformer-based":[31,49],"models":[32,50],"are":[33],"challenging":[34],"to":[35,77,118,130,142,149],"strike":[36],"better":[38],"balance":[39],"between":[40,81],"performance":[41,170],"efficiency.":[43,84],"The":[44,85,208],"computational":[45,121,206],"complexity":[46],"the":[48,54,72,79,106,114,120,143,165,196,201],"is":[51,111,128],"quadratic":[52],"number":[55],"inputs,":[57],"which":[58,199],"severely":[59],"hinders":[60],"application":[62],"dense":[64],"prediction":[65],"tasks.":[66],"In":[67,105],"this":[68,138],"paper,":[69],"we":[70,135,161],"present":[71],"semantic-aware":[73],"dimension-pooling":[74,109,139],"transformer":[75,91],"(SDPT)":[76],"mitigate":[78],"conflict":[80],"accuracy":[82],"proposed":[86,166],"model":[87],"comprises":[88],"an":[89],"efficient":[90],"encoder":[92],"for":[93,101],"generating":[94],"hierarchical":[95],"features":[96],"semantic-balanced":[99],"decoder":[100,144],"predicting":[102],"semantic":[103],"masks.":[104],"encoder,":[107],"mechanism":[110],"used":[112,129],"multi-head":[115],"self-attention":[116],"(MHSA)":[117],"reduce":[119],"cost,":[122],"parallel":[125],"depth-wise":[126],"convolution":[127],"capture":[131],"local":[132],"semantics.":[133],"Simultaneously,":[134],"further":[136],"apply":[137],"attention":[140],"(DPA)":[141],"as":[145],"refinement":[147],"module":[148],"integrate":[150],"multi-level":[151],"features.":[152],"With":[153],"such":[154],"simple":[156],"yet":[157],"powerful":[158],"encoder-decoder":[159],"framework,":[160],"empirically":[162],"demonstrate":[163],"that":[164],"SDPT":[167,185],"achieves":[168,186],"excellent":[169],"efficiency":[172],"on":[173,195],"various":[174],"popular":[175],"benchmarks,":[176],"including":[177],"ADE20K,":[178],"Cityscapes,":[179],"COCO-Stuff.":[181],"For":[182],"example,":[183],"our":[184],"48.6":[187],"<inline-formula":[188],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[189],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[190],"<tex-math":[191],"notation=\"LaTeX\">$\\%$</tex-math>":[192],"</inline-formula>":[193],"mIOU":[194],"ADE20K":[197],"dataset,":[198],"outperforms":[200],"current":[202],"methods":[203],"fewer":[205],"costs.":[207],"codes":[209],"can":[210],"be":[211],"found":[212],"at":[213],"https://github.com/HuCaoFighting/SDPT.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}