{"id":"https://openalex.org/W7171961243","doi":"https://doi.org/10.1145/3774521.3774625","title":"TranSMOTE: Transformer Based Synthetic Minority Oversampling Technique","display_name":"TranSMOTE: Transformer Based Synthetic Minority Oversampling Technique","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7171961243","doi":"https://doi.org/10.1145/3774521.3774625"},"language":null,"primary_location":{"id":"doi:10.1145/3774521.3774625","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774625","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774521.3774625","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111227069","display_name":"Priyobrata Mondal","orcid":null},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Priyobrata Mondal","raw_affiliation_strings":["Electronics and Communication Sciences Unit, Indian Statistical Institute, Kolkata, West Bengal, India"],"raw_orcid":"https://orcid.org/0009-0007-8484-5930","affiliations":[{"raw_affiliation_string":"Electronics and Communication Sciences Unit, Indian Statistical Institute, Kolkata, West Bengal, India","institution_ids":["https://openalex.org/I6498739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144167896","display_name":"Soumi Pal","orcid":"https://orcid.org/0009-0001-0806-811X"},"institutions":[{"id":"https://openalex.org/I115715567","display_name":"Birla Institute of Technology, Mesra","ror":"https://ror.org/028vtqb15","country_code":"IN","type":"education","lineage":["https://openalex.org/I115715567"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Soumi Pal","raw_affiliation_strings":["Department of Mathematics, Birla Institute of Technology, Mesra, Ranchi, Jharkhand, India"],"raw_orcid":"https://orcid.org/0009-0001-0806-811X","affiliations":[{"raw_affiliation_string":"Department of Mathematics, Birla Institute of Technology, Mesra, Ranchi, Jharkhand, India","institution_ids":["https://openalex.org/I115715567"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000078546","display_name":"Swagatam Das","orcid":"https://orcid.org/0000-0001-6843-4508"},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Swagatam Das","raw_affiliation_strings":["Electronics and Communication Sciences Unit, Indian Statistical Institute, Kolkata, West Bengal, India"],"raw_orcid":"https://orcid.org/0000-0001-6843-4508","affiliations":[{"raw_affiliation_string":"Electronics and Communication Sciences Unit, Indian Statistical Institute, Kolkata, West Bengal, India","institution_ids":["https://openalex.org/I6498739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.8195000290870667},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5979999899864197},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5393000245094299},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5073000192642212},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4950999915599823},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.43230000138282776},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4318999946117401},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.3684999942779541},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3662000000476837}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.8195000290870667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7333999872207642},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5979999899864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5766000151634216},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5393000245094299},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5073000192642212},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4968000054359436},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4318999946117401},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.3684999942779541},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2833999991416931},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2614000141620636}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774521.3774625","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774625","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774521.3774625","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774625","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2104933073","https://openalex.org/W2117876524","https://openalex.org/W2126996952","https://openalex.org/W2132791018","https://openalex.org/W2148143831","https://openalex.org/W2590780569","https://openalex.org/W2601726217","https://openalex.org/W2948978827","https://openalex.org/W2981515171","https://openalex.org/W3030391949","https://openalex.org/W4206162816","https://openalex.org/W4282919843","https://openalex.org/W4385488654","https://openalex.org/W4399568552","https://openalex.org/W4404641467","https://openalex.org/W4404654652","https://openalex.org/W4405221409","https://openalex.org/W4405962054","https://openalex.org/W4406191294","https://openalex.org/W4406263598","https://openalex.org/W4406610597","https://openalex.org/W4409795900","https://openalex.org/W4410990322","https://openalex.org/W4411169754","https://openalex.org/W4411921291","https://openalex.org/W4412170755","https://openalex.org/W4413147685","https://openalex.org/W4414195271","https://openalex.org/W4414198572","https://openalex.org/W4416583105"],"related_works":[],"abstract_inverted_index":{"Class":[0],"imbalance":[1,98,224],"poses":[2],"a":[3,37,83,136,218],"fundamental":[4],"challenge":[5],"in":[6,99,105],"deep":[7,61],"learning,":[8],"where":[9],"minority":[10],"classes":[11],"are":[12],"systematically":[13],"underrepresented,":[14],"leading":[15],"to":[16,47,95,204],"biased":[17],"models":[18],"with":[19,92,141],"poor":[20],"generalization":[21],"on":[22,184,194,197,201],"critical":[23],"but":[24],"rare":[25],"instances.":[26],"While":[27],"the":[28,56,106,205,227],"Synthetic":[29],"Minority":[30],"Oversampling":[31],"Technique":[32],"(SMOTE)":[33],"has":[34],"emerged":[35],"as":[36],"cornerstone":[38],"solution":[39],"for":[40,221,232],"traditional":[41],"feature":[42],"spaces,":[43],"its":[44],"direct":[45],"application":[46],"high-dimensional":[48],"image":[49,100],"data":[50],"suffers":[51],"from":[52,76],"semantic":[53],"incoherence":[54],"and":[55,74,126,154,172,199,212],"curse":[57],"of":[58,192,230],"dimensionality.":[59],"Concurrently,":[60],"generative":[62],"approaches,":[63],"despite":[64],"their":[65],"sophistication,":[66],"often":[67],"lack":[68],"fine-grained":[69],"control":[70],"over":[71],"interpolation":[72,119],"processes":[73],"suffer":[75],"training":[77,213],"instabilities.":[78],"This":[79],"paper":[80],"introduces":[81],"TranSMOTE,":[82],"novel":[84],"framework":[85],"that":[86,175],"synergistically":[87],"combines":[88],"Vision":[89,115,137],"Transformer":[90,138],"architectures":[91],"SMOTE-based":[93,145],"oversampling":[94],"address":[96],"class":[97,223],"classification.":[101],"Our":[102,215],"approach":[103,216],"operates":[104],"semantically":[107,233],"rich":[108],"patch":[109,124,151],"token":[110,147,152],"embedding":[111],"space":[112],"learned":[113],"by":[114,225],"Transformers,":[116],"enabling":[117],"principled":[118],"while":[120,208],"preserving":[121],"both":[122],"local":[123],"characteristics":[125],"global":[127],"spatial":[128],"relationships.":[129],"The":[130],"methodology":[131],"comprises":[132],"three":[133],"distinct":[134],"phases:":[135],"autoencoder":[139],"trained":[140],"multi-objective":[142],"loss":[143],"functions,":[144],"synthetic":[146,235],"generation":[148],"through":[149],"concatenated":[150],"interpolation,":[153],"systematic":[155],"evaluation":[156,186],"using":[157],"downstream":[158],"classification":[159],"tasks.":[160],"Extensive":[161],"experimental":[162],"validation":[163],"across":[164],"five":[165],"benchmark":[166],"datasets":[167],"(MNIST,":[168],"Fashion-MNIST,":[169],"CIFAR-10,":[170,198],"SVHN,":[171],"GTSRB)":[173],"demonstrates":[174],"TranSMOTE":[176,188],"consistently":[177],"outperforms":[178],"state-of-the-art":[179],"methods,":[180],"achieving":[181],"superior":[182],"performance":[183],"various":[185],"metrics.":[187],"achieves":[189],"remarkable":[190],"improvements":[191],"1.7%":[193],"MNIST,":[195],"2.6%":[196],"6.5%":[200],"SVHN":[202],"compared":[203],"strongest":[206],"baselines,":[207],"maintaining":[209],"computational":[210],"efficiency":[211],"stability.":[214],"establishes":[217],"new":[219],"paradigm":[220],"addressing":[222],"leveraging":[226],"representational":[228],"power":[229],"transformers":[231],"meaningful":[234],"sample":[236],"generation.":[237]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}