{"id":"W2981720610","doi":"10.1109/iccv.2019.00149","title":"Moment Matching for Multi-Source Domain Adaptation","year":2019,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1574,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute","funders":"","keywords":"Computer science; Matching (statistics); Source code; Domain (mathematical analysis); Benchmarking; Adaptation (eye); Domain adaptation; Moment (physics); Transfer of learning; Feature (linguistics); Artificial intelligence; Code (set theory); Data mining; Machine learning; Pattern recognition (psychology); Set (abstract data type); Mathematics; Statistics","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":[0.001533574,0.0009515039,0.001052577,0.001480787,0.0005382074,0.0009611759,0.002063135,0.001423491,0.003102393],"category_scores_gemma":[0.006538243,0.0004610359,0.001112282,0.001681766,0.0009186447,0.002639069,0.002306469,0.00245775,0.001817467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000866684,"about_ca_system_score_gemma":0.0008241145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0029036,"about_ca_topic_score_gemma":0.003848172,"domain_scores_codex":[0.9989672,0.00027499,0.00004855241,0.0004345589,0.0001899677,0.0000848135],"domain_scores_gemma":[0.9979845,0.0007270977,0.0001462169,0.000768188,0.0002871629,0.00008670704],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005169886,0.0003281995,0.003894319,0.0003869168,0.0002510252,0.000324967,0.0002480092,0.3278632,0.03271873,0.02682539,0.02482524,0.581817],"study_design_scores_gemma":[0.00001799711,0.0000368899,0.0009589221,0.00001749618,0.00001796758,0.0001573386,0.00003651896,0.9569454,0.008776713,0.02783212,0.005172682,0.00002995609],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0147288,0.0005724727,0.9791576,0.0002128604,0.0001048973,0.00006944219,0.0007581033,0.002719728,0.00167607],"genre_scores_gemma":[0.4597828,0.0007163972,0.5250393,0.000537334,0.0001820147,0.0003228383,0.0072626,0.0006420711,0.005514727],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003102393,"threshold_uncertainty_score":0.01037854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03986913152636868,"score_gpt":0.2770098568088324,"score_spread":0.2371407252824638,"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."}}