{"id":"https://openalex.org/W4386590518","doi":"https://doi.org/10.1109/icip49359.2023.10222606","title":"Attention-Guided Contrastive Masked Image Modeling for Transformer-Based Self-Supervised Learning","display_name":"Attention-Guided Contrastive Masked Image Modeling for Transformer-Based Self-Supervised Learning","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386590518","doi":"https://doi.org/10.1109/icip49359.2023.10222606"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10222606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","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/A5102554256","display_name":"Yucheng Zhan","orcid":"https://orcid.org/0009-0004-6898-6264"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yucheng Zhan","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108730758","display_name":"Yucheng Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yucheng Zhao","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101437627","display_name":"Chong Luo","orcid":"https://orcid.org/0000-0003-0939-474X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chong Luo","raw_affiliation_strings":["Microsoft Research Asia,Beijing,China","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103136560","display_name":"Yueyi Zhang","orcid":"https://orcid.org/0000-0003-0788-8826"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueyi Zhang","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100656317","display_name":"Xiaoyan Sun","orcid":"https://orcid.org/0000-0003-3638-5566"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Sun","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102554256"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.3491,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.654616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2490","last_page":"2494"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994000196456909,"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":0.996999979019165,"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/T12676","display_name":"Machine Learning and ELM","score":0.9785000085830688,"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":0.6928889751434326},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6079866290092468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5540708303451538},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3759286403656006},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35799700021743774},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35482072830200195},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3209119439125061},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1417759358882904},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09824347496032715},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.076814204454422}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6928889751434326},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6079866290092468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5540708303451538},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3759286403656006},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35799700021743774},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35482072830200195},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3209119439125061},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1417759358882904},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09824347496032715},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.076814204454422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10222606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2063971957","https://openalex.org/W2194775991","https://openalex.org/W3035524453","https://openalex.org/W3128661784","https://openalex.org/W3145450063","https://openalex.org/W3159481202","https://openalex.org/W3160566314","https://openalex.org/W3192404838","https://openalex.org/W3215023121","https://openalex.org/W4312312750","https://openalex.org/W4312804044","https://openalex.org/W4313070576","https://openalex.org/W4313156423","https://openalex.org/W4382465386","https://openalex.org/W6774314701","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6794295097","https://openalex.org/W6796761347","https://openalex.org/W6803844357"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2779427294","https://openalex.org/W2775347418","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W3003936178","https://openalex.org/W2145652935","https://openalex.org/W2563206327","https://openalex.org/W2069885731"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,18],"with":[2],"vision":[3],"transformer":[4],"(ViT)":[5],"has":[6,88],"gained":[7],"much":[8],"attention":[9,79,100],"recently.":[10],"Most":[11],"existing":[12],"methods":[13],"rely":[14],"on":[15],"either":[16],"contrastive":[17],"or":[19],"masked":[20,96,107],"image":[21],"modeling.":[22],"The":[23,36,126],"former":[24],"is":[25,145],"suitable":[26],"for":[27,83],"global":[28,104],"feature":[29],"extraction":[30],"but":[31,44],"underperforms":[32],"in":[33],"fine-grained":[34],"tasks.":[35],"later":[37],"explores":[38],"the":[39,46,71,78,93,103],"internal":[40],"structure":[41],"of":[42,73,81,95,106],"images":[43],"ignores":[45],"high":[47],"information":[48,52],"sparsity":[49],"and":[50,76,101,108,121,141],"unbalanced":[51],"distribution.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57],"propose":[58],"a":[59],"new":[60],"approach":[61],"called":[62],"Attention-guided":[63],"Contrastive":[64],"Masked":[65],"Image":[66],"Modeling":[67],"(ACoMIM),":[68],"which":[69],"integrates":[70],"merits":[72],"both":[74],"paradigms":[75],"leverages":[77],"mechanism":[80],"ViT":[82],"effective":[84],"representation.":[85],"Specifically,":[86],"it":[87],"two":[89,115],"pretext":[90,116],"tasks,":[91],"predicting":[92],"features":[94,105],"regions":[97],"guided":[98],"by":[99],"comparing":[102],"unmasked":[109],"images.":[110],"We":[111],"show":[112],"that":[113,129],"these":[114],"tasks":[117,137],"complement":[118],"each":[119],"other":[120],"improve":[122],"our":[123,130],"method\u2019s":[124],"performance.":[125],"experiments":[127],"demonstrate":[128],"model":[131],"transfers":[132],"well":[133],"to":[134],"various":[135],"downstream":[136],"such":[138],"as":[139],"classification":[140],"object":[142],"detection.":[143],"Code":[144],"available":[146],"at":[147],"https://github.com/yczhan/ACoMIM.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-11T23:09:37.256380","created_date":"2025-10-10T00:00:00"}
