{"id":"https://openalex.org/W7143522096","doi":"https://doi.org/10.48550/arxiv.2603.26393","title":"Adapting Frozen Mono-modal Backbones for Multi-modal Registration via Contrast-Agnostic Instance Optimization","display_name":"Adapting Frozen Mono-modal Backbones for Multi-modal Registration via Contrast-Agnostic Instance Optimization","publication_year":2026,"publication_date":"2026-03-27","ids":{"openalex":"https://openalex.org/W7143522096","doi":"https://doi.org/10.48550/arxiv.2603.26393"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.26393","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26393","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.2603.26393","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130998130","display_name":"Yi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038961260","display_name":"Yidong Zhao","orcid":"https://orcid.org/0000-0003-3953-6921"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yidong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130970925","display_name":"Qian Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao, Qian","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.26089999079704285,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.26089999079704285,"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":0.2012999951839447,"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":0.19910000264644623,"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/pipeline","display_name":"Pipeline (software)","score":0.5444999933242798},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5245000123977661},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4948999881744385},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4797999858856201},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4526999890804291},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43380001187324524},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.39480000734329224},{"id":"https://openalex.org/keywords/image-registration","display_name":"Image registration","score":0.3910999894142151},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3856000006198883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893999814987183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.670199990272522},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5444999933242798},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5245000123977661},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4948999881744385},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4797999858856201},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4526999890804291},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4032999873161316},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C166704113","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image registration","level":3,"score":0.3910999894142151},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.37770000100135803},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3301999866962433},{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.31150001287460327},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2750000059604645},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.26260000467300415},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25940001010894775},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C180462255","wikidata":"https://www.wikidata.org/wiki/Q3559736","display_name":"Standard test image","level":4,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.26393","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26393","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.2603.26393","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26393","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deformable":[0],"image":[1,9,114],"registration":[2,97,105],"remains":[3],"a":[4,96,101,108],"central":[5],"challenge":[6],"in":[7,64,71,82,84,210],"medical":[8],"analysis,":[10],"particularly":[11],"under":[12,36],"multi-modal":[13,198,236],"scenarios":[14],"where":[15],"intensity":[16],"distributions":[17],"vary":[18],"significantly":[19],"across":[20],"scans.":[21],"While":[22],"deep":[23,57],"learning":[24],"methods":[25],"provide":[26],"efficient":[27],"feed-forward":[28],"predictions,":[29],"they":[30],"often":[31],"fail":[32],"to":[33,129,145,164,166],"generalize":[34],"robustly":[35],"distribution":[37],"shifts":[38],"at":[39,138],"test":[40,139],"time.":[41,140],"A":[42],"straightforward":[43],"remedy":[44],"is":[45,61,143],"full":[46,158],"network":[47],"fine-tuning,":[48],"yet":[49],"for":[50,112],"modern":[51],"architectures":[52],"such":[53],"as":[54],"Transformers":[55],"or":[56],"U-Nets,":[58],"this":[59,92],"adaptation":[60,110,223],"prohibitively":[62],"expensive":[63],"both":[65],"memory":[66],"and":[67,126,132,180,205,224,231],"runtime":[68],"when":[69],"operating":[70],"3D.":[72],"Meanwhile,":[73],"the":[74,85,146,154,162,174,185,192,197,202],"naive":[75],"fine-tuning":[76,159],"struggles":[77],"more":[78],"with":[79,107,135,221],"potential":[80],"degradation":[81],"performance":[83],"existence":[86],"of":[87,148,157],"drastic":[88],"domain":[89,133],"shifts.":[90],"In":[91,190],"work,":[93],"we":[94,117],"propose":[95],"framework":[98],"that":[99,216],"integrates":[100],"frozen":[102,218],"pretrained":[103,186],"\\textbf{mono-modal}":[104],"model":[106],"lightweight":[109,225],"pipeline":[111],"\\textbf{multi-modal}":[113],"registration.":[115,237],"Specifically,":[116],"employ":[118],"style":[119],"transfer":[120],"based":[121],"on":[122,173,196,201],"contrast-agnostic":[123],"representation":[124],"generation":[125],"refinement":[127],"modules":[128],"bridge":[130],"modality":[131,222],"gaps":[134],"instance":[136,226],"optimization":[137,227],"This":[141],"design":[142],"orthogonal":[144],"choice":[147],"backbone":[149],"mono-modal":[150,188,219],"model,":[151],"thus":[152],"avoids":[153],"computational":[155],"burden":[156],"while":[160],"retaining":[161],"flexibility":[163],"adapt":[165],"unseen":[167],"domains.":[168],"We":[169],"evaluate":[170],"our":[171],"approach":[172],"Learn2Reg":[175],"2025":[176],"LUMIR":[177],"validation":[178],"set":[179],"observe":[181],"consistent":[182],"improvements":[183],"over":[184],"state-of-the-art":[187],"backbone.":[189],"particular,":[191],"method":[193],"ranks":[194],"second":[195],"subset,":[199,204],"third":[200],"out-of-domain":[203],"achieves":[206],"fourth":[207],"place":[208],"overall":[209],"Dice":[211],"score.":[212],"These":[213],"results":[214],"demonstrate":[215],"combining":[217],"models":[220],"offers":[228],"an":[229],"effective":[230],"practical":[232],"pathway":[233],"toward":[234],"robust":[235]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-31T00:00:00"}