{"id":"https://openalex.org/W7131808815","doi":"https://doi.org/10.1109/sii64115.2026.11404616","title":"Evaluating the Out-of-Distribution Generalization of Robot Diffusion Policies under the DINOv2 Visual Encoder","display_name":"Evaluating the Out-of-Distribution Generalization of Robot Diffusion Policies under the DINOv2 Visual Encoder","publication_year":2026,"publication_date":"2026-01-11","ids":{"openalex":"https://openalex.org/W7131808815","doi":"https://doi.org/10.1109/sii64115.2026.11404616"},"language":null,"primary_location":{"id":"doi:10.1109/sii64115.2026.11404616","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii64115.2026.11404616","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/SICE International Symposium on System Integration (SII)","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/A5127281862","display_name":"\u00c1ngel Montejo","orcid":null},"institutions":[{"id":"https://openalex.org/I184886455","display_name":"Maersk (Denmark)","ror":"https://ror.org/046gbzb64","country_code":"DK","type":"company","lineage":["https://openalex.org/I184886455"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"\u00c1ngel Montejo","raw_affiliation_strings":["University of Southern Denmark,SDU Robotics, The Maersk Mc-Kinney Moller Insitute, Faculty of Engineering,Odense,Denmark,5230"],"affiliations":[{"raw_affiliation_string":"University of Southern Denmark,SDU Robotics, The Maersk Mc-Kinney Moller Insitute, Faculty of Engineering,Odense,Denmark,5230","institution_ids":["https://openalex.org/I184886455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064712655","display_name":"I\u00f1igo Iturrate","orcid":"https://orcid.org/0000-0001-7922-1946"},"institutions":[{"id":"https://openalex.org/I184886455","display_name":"Maersk (Denmark)","ror":"https://ror.org/046gbzb64","country_code":"DK","type":"company","lineage":["https://openalex.org/I184886455"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"I\u00f1igo Iturrate","raw_affiliation_strings":["University of Southern Denmark,SDU Robotics, The Maersk Mc-Kinney Moller Insitute, Faculty of Engineering,Odense,Denmark,5230"],"affiliations":[{"raw_affiliation_string":"University of Southern Denmark,SDU Robotics, The Maersk Mc-Kinney Moller Insitute, Faculty of Engineering,Odense,Denmark,5230","institution_ids":["https://openalex.org/I184886455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5127281862"],"corresponding_institution_ids":["https://openalex.org/I184886455"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.91303409,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.08940000087022781,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.08940000087022781,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.057999998331069946,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.05260000005364418,"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":0.6409000158309937},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6402000188827515},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.6028000116348267},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5981000065803528},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5103999972343445},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49549999833106995},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.42910000681877136},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4284000098705292},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.414900004863739}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6787999868392944},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6766999959945679},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6409000158309937},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6402000188827515},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6028000116348267},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5981000065803528},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5637000203132629},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5103999972343445},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49549999833106995},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3140999972820282},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C2776126113","wikidata":"https://www.wikidata.org/wiki/Q1128980","display_name":"Industrial robot","level":3,"score":0.3102000057697296},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2935999929904938},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2921000123023987},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C10912380","wikidata":"https://www.wikidata.org/wiki/Q527952","display_name":"Visual servoing","level":3,"score":0.2687000036239624},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sii64115.2026.11404616","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii64115.2026.11404616","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/SICE International Symposium on System Integration (SII)","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":12,"referenced_works":["https://openalex.org/W2125188427","https://openalex.org/W2194775991","https://openalex.org/W2963634205","https://openalex.org/W3159481202","https://openalex.org/W4401414814","https://openalex.org/W4402354045","https://openalex.org/W4403337227","https://openalex.org/W4409262207","https://openalex.org/W4413925003","https://openalex.org/W4413926203","https://openalex.org/W4413945067","https://openalex.org/W4415593660"],"related_works":[],"abstract_inverted_index":{"The":[0],"generalizability":[1],"of":[2,25],"visuomotor":[3],"policy":[4,50,125],"models":[5],"is":[6,19],"crucial":[7],"for":[8,88,124],"their":[9],"real-world":[10],"usefulness":[11],"in":[12,65,75],"settings":[13],"such":[14],"as":[15],"industrial":[16],"environments.":[17],"This":[18],"heavily":[20],"impacted":[21],"by":[22,41],"the":[23,33,49,104,120],"choice":[24],"visual":[26,36,54,122],"encoder.":[27],"In":[28],"this":[29,64],"paper,":[30],"we":[31,83],"integrate":[32],"DINOv2":[34,121],"foundation":[35],"encoder":[37,123],"with":[38],"Diffusion":[39],"Policy":[40],"designing":[42],"a":[43],"spatially-aware":[44],"projection":[45],"head,":[46],"that":[47,91,100],"allows":[48],"to":[51],"shape":[52],"its":[53],"representation":[55],"while":[56],"benefiting":[57],"from":[58],"DINOv2\u2019s":[59],"robust":[60],"embeddings.":[61],"We":[62,112],"evaluate":[63],"drastic":[66],"out-of-distribution":[67],"conditions.":[68],"As":[69],"success":[70],"rate":[71],"can":[72],"be":[73],"uninformative":[74],"these":[76],"conditions,":[77],"where":[78],"failure":[79],"rates":[80],"are":[81],"high,":[82],"present":[84],"three":[85],"evaluation":[86],"criteria":[87],"goal-driven":[89],"policies":[90],"remain":[92],"informative":[93],"despite":[94],"task":[95],"failure.":[96],"Our":[97],"result":[98],"shows":[99],"our":[101],"approach":[102],"outperforms":[103],"baseline":[105],"under":[106],"color":[107],"alterations":[108],"and":[109],"camera":[110],"displacements.":[111],"observe":[113],"promising":[114],"emergent":[115],"task-relevant":[116],"feature":[117],"tracking":[118],"using":[119],"learning.":[126]},"counts_by_year":[],"updated_date":"2026-03-01T06:05:34.837733","created_date":"2026-02-28T00:00:00"}