{"id":"https://openalex.org/W4416251591","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228016","title":"Symmetric masking strategy enhances the performance of Masked Image Modeling","display_name":"Symmetric masking strategy enhances the performance of Masked Image Modeling","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251591","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228016"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5065249287","display_name":"Khanh-Duy Nguyen","orcid":"https://orcid.org/0000-0003-4237-2737"},"institutions":[{"id":"https://openalex.org/I4210120052","display_name":"National Cancer Center","ror":"https://ror.org/02tsanh21","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I1290491151","https://openalex.org/I2801339556","https://openalex.org/I4210120052"]},{"id":"https://openalex.org/I4210089431","display_name":"National Cancer Center","ror":"https://ror.org/0065zqt33","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210089431"]}],"countries":["KR","US"],"is_corresponding":true,"raw_author_name":"Khanh Binh Nguyen","raw_affiliation_strings":["National Cancer Center,Cancer Big Data and Artificial Intelligence,Goyang,South Korea"],"affiliations":[{"raw_affiliation_string":"National Cancer Center,Cancer Big Data and Artificial Intelligence,Goyang,South Korea","institution_ids":["https://openalex.org/I4210120052","https://openalex.org/I4210089431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011471384","display_name":"Chae Jung Park","orcid":"https://orcid.org/0000-0002-1261-307X"},"institutions":[{"id":"https://openalex.org/I4210089431","display_name":"National Cancer Center","ror":"https://ror.org/0065zqt33","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210089431"]},{"id":"https://openalex.org/I4210120052","display_name":"National Cancer Center","ror":"https://ror.org/02tsanh21","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I1290491151","https://openalex.org/I2801339556","https://openalex.org/I4210120052"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Chae Jung Park","raw_affiliation_strings":["National Cancer Center,Cancer Big Data and Artificial Intelligence,Goyang,South Korea"],"affiliations":[{"raw_affiliation_string":"National Cancer Center,Cancer Big Data and Artificial Intelligence,Goyang,South Korea","institution_ids":["https://openalex.org/I4210120052","https://openalex.org/I4210089431"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065249287"],"corresponding_institution_ids":["https://openalex.org/I4210089431","https://openalex.org/I4210120052"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37480722,"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":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.3109999895095825,"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":0.3109999895095825,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.3068000078201294,"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":0.0860000029206276,"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/masking","display_name":"Masking (illustration)","score":0.7476999759674072},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5509999990463257},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4869999885559082},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.47870001196861267},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.43309998512268066},{"id":"https://openalex.org/keywords/visual-masking","display_name":"Visual masking","score":0.4235999882221222},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3652999997138977},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.36070001125335693}],"concepts":[{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.7476999759674072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178000211715698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7089999914169312},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5728999972343445},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5509999990463257},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4869999885559082},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.47870001196861267},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C2779200073","wikidata":"https://www.wikidata.org/wiki/Q18395575","display_name":"Visual masking","level":4,"score":0.4235999882221222},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.36070001125335693},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.35580000281333923},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.34380000829696655},{"id":"https://openalex.org/C2779627259","wikidata":"https://www.wikidata.org/wiki/Q779763","display_name":"Pretext","level":3,"score":0.32120001316070557},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.29319998621940613},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2930000126361847},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2766999900341034},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":25,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2161969291","https://openalex.org/W2737258237","https://openalex.org/W2797977484","https://openalex.org/W2883725317","https://openalex.org/W2884822772","https://openalex.org/W2963150697","https://openalex.org/W2987741655","https://openalex.org/W3035524453","https://openalex.org/W3145450063","https://openalex.org/W3159481202","https://openalex.org/W3176659256","https://openalex.org/W3180355996","https://openalex.org/W4285164317","https://openalex.org/W4312312750","https://openalex.org/W4312446817","https://openalex.org/W4312685069","https://openalex.org/W4312804044","https://openalex.org/W4313156423","https://openalex.org/W4382465386","https://openalex.org/W4386065811","https://openalex.org/W4386076084","https://openalex.org/W4386221015","https://openalex.org/W4390874575"],"related_works":[],"abstract_inverted_index":{"Masked":[0],"Image":[1],"Modeling":[2],"(MIM)":[3],"is":[4,136],"a":[5,34,110,140],"technique":[6],"in":[7,25],"self-supervised":[8],"learning":[9],"that":[10,114],"focuses":[11],"on":[12,57,125,146],"acquiring":[13],"detailed":[14],"visual":[15],"representations":[16],"from":[17],"unlabeled":[18],"images":[19],"by":[20],"estimating":[21],"the":[22,38,58,64,74,83,117],"missing":[23],"pixels":[24],"randomly":[26],"masked":[27],"sections.":[28],"It":[29],"has":[30],"proven":[31],"to":[32,62,72,85,92],"be":[33,80,86,100],"powerful":[35],"tool":[36],"for":[37,88,102,134],"preliminary":[39],"training":[40,132],"of":[41,144],"Vision":[42],"Transformers":[43],"(ViTs),":[44],"yielding":[45],"impressive":[46],"results":[47],"across":[48,154],"various":[49],"tasks.":[50],"Nevertheless,":[51],"most":[52],"MIM":[53,135],"methods":[54],"heavily":[55],"depend":[56],"random":[59],"masking":[60,112,127],"strategy":[61,68,113],"formulate":[63],"pretext":[65],"task.":[66],"This":[67],"necessitates":[69],"numerous":[70],"trials":[71],"ascertain":[73],"optimal":[75],"dropping":[76],"ratio,":[77],"which":[78],"can":[79],"resource-intensive,":[81],"requiring":[82],"model":[84,118],"pre-trained":[87],"anywhere":[89],"between":[90],"800":[91],"1600":[93],"epochs.":[94],"Furthermore,":[95],"this":[96,106,126],"approach":[97],"may":[98],"not":[99],"suitable":[101],"all":[103],"datasets.":[104],"In":[105],"work,":[107],"we":[108],"propose":[109],"new":[111,141],"effectively":[115],"helps":[116],"capture":[119],"global":[120],"and":[121,150,168],"local":[122],"features.":[123],"Based":[124],"strategy,":[128],"SymMIM,":[129],"our":[130],"proposed":[131],"pipeline":[133],"introduced.":[137],"SymMIM":[138],"achieves":[139],"SOTA":[142,153],"accuracy":[143],"85.9%":[145],"ImageNet":[147],"using":[148],"ViT-Large":[149],"surpasses":[151],"previous":[152],"downstream":[155],"tasks":[156],"such":[157],"as":[158],"image":[159],"classification,":[160],"semantic":[161],"segmentation,":[162],"object":[163],"detection,":[164],"instance":[165],"segmentation":[166],"tasks,":[167],"so":[169],"on.":[170]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}