{"id":"W4412866368","doi":"10.1088/2632-2153/adf701","title":"SIDDA: SInkhorn Dynamic Domain Adaptation for image classification with equivariant neural networks","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Theoretical Astrophysics; University of Toronto","funders":"Fermilab; Oak Ridge Institute for Science and Education; National Science Foundation","keywords":"Equivariant map; Domain adaptation; Adaptation (eye); Computer science; Domain (mathematical analysis); Image (mathematics); Artificial neural network; Artificial intelligence; Pattern recognition (psychology); Mathematics; Pure mathematics; Psychology; Mathematical analysis; Neuroscience","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001043936,0.0007399452,0.0007186797,0.0005103012,0.0003519174,0.0006827332,0.001512528,0.0009576867,0.00207083],"category_scores_gemma":[0.00295781,0.0003470904,0.000711995,0.0004771957,0.0007406274,0.0008703823,0.001356244,0.002100932,0.0006646972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007272349,"about_ca_system_score_gemma":0.0006773162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002749318,"about_ca_topic_score_gemma":0.00357994,"domain_scores_codex":[0.9996043,0.0001365289,0.00002431773,0.0001071425,0.00008852438,0.00003916776],"domain_scores_gemma":[0.9991405,0.0003522701,0.00008072178,0.0001635506,0.0002010922,0.00006188935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001466344,0.0001044607,0.001839609,0.00006904139,0.00008210559,0.00009534294,0.00008984006,0.7559026,0.009875281,0.00956172,0.003220177,0.2190132],"study_design_scores_gemma":[0.000002370117,0.00001189614,0.00004872364,0.0000017452,0.000001185348,0.000006148168,0.000003821608,0.9971725,0.000758237,0.001718327,0.0002723832,0.000002677044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02958458,0.0002266891,0.9671709,0.00014033,0.0000667837,0.0000369405,0.00005660858,0.001523803,0.001193321],"genre_scores_gemma":[0.6152557,0.0001432516,0.3797003,0.0003662875,0.00005028432,0.0001436366,0.0004715333,0.0002579595,0.003611037],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002749318,"threshold_uncertainty_score":0.006927669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009021148630347827,"score_gpt":0.2581942054823836,"score_spread":0.2491730568520358,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}