{"id":"https://openalex.org/W7165922346","doi":"https://doi.org/10.48550/arxiv.2606.25784","title":"$S^{2}$-FracMix: Label-Preserving Self-Saliency Mixup Augmentation","display_name":"$S^{2}$-FracMix: Label-Preserving Self-Saliency Mixup Augmentation","publication_year":2026,"publication_date":"2026-06-24","ids":{"openalex":"https://openalex.org/W7165922346","doi":"https://doi.org/10.48550/arxiv.2606.25784"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.25784","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.25784","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.25784","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138489246","display_name":"K M Sajjadul Islam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Islam, Khawar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139312332","display_name":"Arif Mahmood","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahmood, Arif","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139370335","display_name":"Xin Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139376955","display_name":"Naveed Akhtar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akhtar, Naveed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.6650000214576721,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.6650000214576721,"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":0.18320000171661377,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0697999969124794,"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/generalization","display_name":"Generalization","score":0.7059999704360962},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5968000292778015},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5388000011444092},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4869999885559082},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4772000014781952},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.41760000586509705},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3930000066757202},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3750999867916107},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36640000343322754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7584999799728394},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7059999704360962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6625999808311462},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5968000292778015},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5388000011444092},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4869999885559082},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4772000014781952},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46959999203681946},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3930000066757202},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.33739998936653137},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27399998903274536},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2621999979019165},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.25784","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.25784","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.25784","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.25784","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Data":[0],"augmentation":[1,40,126],"is":[2,170],"known":[3],"to":[4,20,36,43],"improve":[5,21],"generalization":[6],"of":[7,39,69,133],"deep":[8],"visual":[9],"models.":[10],"Recent":[11],"methods":[12,144],"favor":[13],"mixup":[14],"strategies":[15],"that":[16,93],"generate":[17],"interpolated":[18],"samples":[19,57],"model":[22,85],"performance.":[23],"However,":[24],"these":[25],"techniques":[26],"not":[27],"only":[28],"incur":[29],"significant":[30],"computational":[31],"overhead,":[32],"they":[33],"also":[34],"lead":[35],"semantic":[37],"disruption":[38],"data":[41],"due":[42],"cross-sample":[44,80],"mixing.":[45],"We":[46,128],"first":[47],"propose":[48],"Self-Saliency":[49],"($S^2$)":[50],"Mixup,":[51],"which":[52],"constructs":[53],"challenging":[54],"yet":[55],"label-consistent":[56],"by":[58,145],"extracting":[59],"multi-scale":[60],"salient":[61,98],"patches":[62],"and":[63,113,123,136,158,164],"reinserting":[64],"them":[65],"into":[66,97],"non-salient":[67],"regions":[68,99],"the":[70,131,142],"same":[71],"image.":[72],"This":[73],"promotes":[74],"scale-invariant":[75],"feature":[76],"learning":[77,110,166],"while":[78],"avoiding":[79],"interference.":[81],"To":[82],"further":[83],"enhance":[84],"robustness,":[86,160],"we":[87],"introduce":[88],"FracMix,":[89],"a":[90,117,121],"mixing":[91],"scheme":[92],"injects":[94],"self-similarity":[95],"patterns":[96],"using":[100],"adaptive":[101],"ratios.":[102],"Collectively,":[103],"our":[104,134],"unified":[105],"framework,":[106],"$S^{2}$-FracMix,":[107],"enables":[108],"simultaneous":[109],"from":[111],"fractal":[112],"non-fractal":[114],"structures":[115],"within":[116],"single":[118],"image,":[119],"yielding":[120],"targeted":[122],"structurally":[124],"coherent":[125],"strategy.":[127],"theoretically":[129],"analyze":[130],"advantage":[132],"technique,":[135],"empirically":[137],"establish":[138],"its":[139],"superiority":[140],"over":[141],"existing":[143],"achieving":[146],"state-of-the-art":[147],"performance":[148],"in":[149],"extensive":[150],"evaluation":[151],"with":[152],"seven":[153],"benchmarks":[154],"across":[155],"classification":[156],"(coarse":[157],"fine-grained),":[159],"calibration,":[161],"object":[162],"detection,":[163],"transfer":[165],"tasks.":[167],"Project":[168],"page":[169],"available":[171],"at":[172],"\\href{https://fracmix-data-augmentation.github.io/}{fracmix-data-augmentation.github.io}":[173]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-26T00:00:00"}