{"id":"https://openalex.org/W7163511079","doi":"https://doi.org/10.48550/arxiv.2606.04888","title":"HD-DinoMoE: A Class-Aware Hierarchical Dual Mixture-of-Experts Network for Scleral Anomaly Segmentation in Complex Acquisition Scenarios","display_name":"HD-DinoMoE: A Class-Aware Hierarchical Dual Mixture-of-Experts Network for Scleral Anomaly Segmentation in Complex Acquisition Scenarios","publication_year":2026,"publication_date":"2026-06-03","ids":{"openalex":"https://openalex.org/W7163511079","doi":"https://doi.org/10.48550/arxiv.2606.04888"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.04888","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04888","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":null,"license_id":null,"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.2606.04888","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055083769","display_name":"Yinxiang Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Yinxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060082727","display_name":"\u50a8\u8302\u7965","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chu, Maoxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137900207","display_name":"Qi Niu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niu, Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137894029","display_name":"Guanghu Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Guanghu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137861022","display_name":"Wei Xu","orcid":"https://orcid.org/0000-0002-7224-1116"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383989","display_name":"Haotian Wang","orcid":"https://orcid.org/0009-0009-5440-4346"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Haotian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137829298","display_name":"Zhi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137845647","display_name":"Yutian Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Yutian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137893042","display_name":"Yuelong Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Yuelong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137841982","display_name":"Guanghao Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liao, Guanghao","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/T11194","display_name":"Ocular Diseases and Beh\u00e7et\u2019s Syndrome","score":0.39250001311302185,"subfield":{"id":"https://openalex.org/subfields/2731","display_name":"Ophthalmology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11194","display_name":"Ocular Diseases and Beh\u00e7et\u2019s Syndrome","score":0.39250001311302185,"subfield":{"id":"https://openalex.org/subfields/2731","display_name":"Ophthalmology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11438","display_name":"Retinal Imaging and Analysis","score":0.15049999952316284,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10997","display_name":"Ocular Surface and Contact Lens","score":0.07670000195503235,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6704000234603882},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5335000157356262},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5273000001907349},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.4375999867916107},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.4253000020980835},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4178999960422516},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.38960000872612},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3885999917984009},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3531999886035919}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6927000284194946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6861000061035156},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6704000234603882},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5335000157356262},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5273000001907349},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.4375999867916107},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4178999960422516},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.38960000872612},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3885999917984009},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35830000042915344},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3531999886035919},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.34850001335144043},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31299999356269836},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C2779104521","wikidata":"https://www.wikidata.org/wiki/Q23058469","display_name":"Contouring","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.29280000925064087},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.04888","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04888","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.04888","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04888","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":null,"license_id":null,"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":{"Traditional":[0],"Chinese":[1],"Medicine":[2],"(TCM)":[3],"ocular":[4,29],"inspection":[5],"provides":[6,203],"empirical":[7],"cues":[8],"for":[9,156,208],"assessing":[10],"scleral":[11,47,65],"surface":[12,48],"anomalies,":[13],"but":[14],"its":[15],"clinical":[16,52],"use":[17],"remains":[18],"subjective":[19],"and":[20,27,43,53,64,93,96,116,122,130,150,153,169,180,216],"difficult":[21],"to":[22,89],"quantify.":[23],"To":[24],"support":[25],"intelligent":[26],"quantifiable":[28],"inspection,":[30],"this":[31],"study":[32],"presents":[33],"the":[34,137,190,194],"TCM-inspired":[35],"Artificial":[36],"Intelligence":[37],"Ocular":[38],"Auxiliary":[39],"Diagnosis":[40],"System":[41],"(TAO)":[42],"focuses":[44],"on":[45,189],"pixel-level":[46],"anomaly":[49,62,158],"segmentation.":[50],"For":[51],"user-acquired":[54],"images":[55],"affected":[56],"by":[57],"multi-source":[58],"distributional":[59],"discrepancies,":[60],"diverse":[61],"morphologies,":[63],"specular":[66],"reflection":[67],"(SSR),":[68],"we":[69],"propose":[70],"HD-DinoMoE,":[71],"a":[72,144,164,170,204],"class-aware":[73,80],"hierarchical":[74],"dual":[75],"mixture-of-experts":[76],"network.":[77],"HD-DinoMoE":[78,162,202],"combines":[79],"dual-stream":[81],"DINOv3":[82],"feature":[83],"fusion":[84],"with":[85,147],"class-specific":[86],"multi-expert":[87],"decoding":[88],"segment":[90],"Vessels,":[91],"Yellow":[92],"Black":[94],"Spots,":[95],"Blood":[97],"Spots.":[98],"A":[99],"three-stage":[100],"backbone-frozen":[101],"routing":[102],"strategy":[103],"stabilizes":[104],"dual-backbone":[105],"adaptation;":[106],"Progressive":[107],"Confidence":[108],"Penalty":[109],"(PCP)":[110],"Loss":[111],"reduces":[112],"high-confidence":[113],"false":[114],"positives":[115],"segmentation":[117,206],"leakage":[118],"in":[119],"SSR":[120],"regions;":[121],"Class-Aware":[123],"Adaptive":[124],"Sample":[125],"Weighting":[126],"(CA-ASW)":[127],"balances":[128],"sample-":[129],"class-level":[131],"training":[132],"contributions.":[133],"We":[134],"further":[135],"construct":[136],"Multi-label":[138],"Scleral":[139],"Anomaly":[140],"Segmentation":[141],"Dataset":[142],"(ML-SASD),":[143],"new":[145],"benchmark":[146],"Clinical,":[148],"Wild,":[149],"Mix":[151],"settings":[152],"pixel-wise":[154],"annotations":[155],"three":[157],"categories.":[159],"On":[160],"ML-SASD-Mix,":[161],"achieves":[163],"mean":[165,171],"Dice":[166],"of":[167,173,193],"72.11%":[168],"Intersection-over-Union":[172],"58.44%,":[174],"while":[175],"maintaining":[176],"favorable":[177],"boundary":[178],"localization":[179],"specular-region":[181],"false-positive":[182],"control.":[183],"It":[184],"also":[185],"shows":[186],"competitive":[187],"generalization":[188],"Vessels":[191],"subset":[192],"public":[195],"SBVPI":[196],"dataset.":[197],"These":[198],"results":[199],"indicate":[200],"that":[201],"feasible":[205],"solution":[207],"TAO":[209],"under":[210],"complex":[211],"acquisition":[212],"scenarios.":[213],"The":[214],"code":[215],"data":[217],"access":[218],"information":[219],"are":[220],"available":[221],"at":[222],"https://github.com/FX-CMX/HD-DinoMoE.":[223]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-05T00:00:00"}