{"id":"W2821744580","doi":"10.1007/978-3-030-30671-7_2","title":"M-ADDA: Unsupervised Domain Adaptation with Deep Metric Learning","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Discriminative model; Computer science; MNIST database; Metric (unit); Artificial intelligence; Adaptation (eye); Pattern recognition (psychology); Domain adaptation; Domain (mathematical analysis); Task (project management); Code (set theory); Function (biology); Machine learning; Source code; Deep learning; Mathematics; Set (abstract data type)","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":[0.001257793,0.001504188,0.002039199,0.001171532,0.0006673135,0.001236285,0.003683455,0.002070594,0.004741571],"category_scores_gemma":[0.003475277,0.0008174657,0.001463909,0.001329561,0.0007458058,0.002348331,0.004146509,0.003929007,0.003682593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008514625,"about_ca_system_score_gemma":0.001190676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00574645,"about_ca_topic_score_gemma":0.009576629,"domain_scores_codex":[0.998926,0.0002869427,0.00004456315,0.0004066324,0.0002356534,0.0001002319],"domain_scores_gemma":[0.9989586,0.0003014819,0.00004532458,0.0004478336,0.0001591848,0.00008751645],"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":[0.0003110705,0.0003993771,0.0009574157,0.0002357429,0.0002892851,0.0001465448,0.00008291264,0.1140723,0.01437473,0.01556584,0.04177666,0.8117881],"study_design_scores_gemma":[0.00001640262,0.00003922574,0.0001988805,0.00001050067,0.00001691688,0.00006055595,0.00001427235,0.9755875,0.004517192,0.01591353,0.003608877,0.0000161535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004659634,0.0004697089,0.9836278,0.0001318081,0.0001535843,0.00006377258,0.0003793635,0.009468268,0.001046118],"genre_scores_gemma":[0.147418,0.0004387441,0.8373072,0.0005614542,0.0001579439,0.0003209672,0.003654203,0.001527285,0.008614253],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00574645,"threshold_uncertainty_score":0.01586217,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03465676586048811,"score_gpt":0.240842660974134,"score_spread":0.2061858951136459,"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."}}