{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005349916,0.0004395136,0.0004754053,0.0004996826,0.0002630617,0.0007557002,0.001325981,0.0002418182,0.0001493208],"category_scores_gemma":[0.0001971806,0.0003833704,0.0001565285,0.001462582,0.0000525842,0.0004187756,0.001032454,0.001422846,0.0003189146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001268025,"about_ca_system_score_gemma":0.0003378593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001104079,"about_ca_topic_score_gemma":0.00004638865,"domain_scores_codex":[0.9966887,0.0003976322,0.0004663294,0.001150273,0.0008625733,0.0004345332],"domain_scores_gemma":[0.9982094,0.0002477881,0.0003620182,0.0006595347,0.0002279945,0.0002932582],"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":[0.00009985274,0.0001252479,0.001465406,0.0002581371,0.0003225307,0.0002257906,0.02335714,0.6299355,0.0002650163,0.1510484,0.0003162039,0.1925808],"study_design_scores_gemma":[0.0008642296,0.0002191524,0.003024309,0.00007136461,0.00002929307,0.00001516866,0.001828099,0.9752067,0.00005472834,0.005481988,0.01251151,0.0006934137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001581338,0.0002951766,0.9685729,0.002171389,0.000325238,0.000414764,8.30896e-7,0.001076824,0.02556157],"genre_scores_gemma":[0.5064074,0.00003968173,0.4915958,0.000836431,0.0001089401,0.00005363668,0.00005041848,0.00004103678,0.0008665946],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5048261,"threshold_uncertainty_score":0.9998618,"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."}}