{"id":"W2903787679","doi":"10.48550/arxiv.1812.08781","title":"Deep Metric Transfer for Label Propagation with Limited Annotated Data","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Generalization; Computer science; Metric (unit); Artificial intelligence; Constraint (computer-aided design); Transfer of learning; Object (grammar); Class (philosophy); Similarity (geometry); Machine learning; Semi-supervised learning; Pattern recognition (psychology); Scheme (mathematics); Image (mathematics); Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004171045,0.0002752127,0.0002676884,0.0004923915,0.0002213803,0.0002102306,0.00229267,0.0002005918,0.00001994943],"category_scores_gemma":[0.00009056076,0.0002758,0.00006262926,0.001573108,0.0001079857,0.0007526972,0.0007474048,0.0003438189,0.00004736365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001021931,"about_ca_system_score_gemma":0.0002275695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003174134,"about_ca_topic_score_gemma":0.00005734314,"domain_scores_codex":[0.9978992,0.0001394584,0.0001962326,0.001298611,0.0001370769,0.000329365],"domain_scores_gemma":[0.9975218,0.0001560271,0.0001551687,0.001566037,0.0004575322,0.0001434705],"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":[0.001424896,0.001169534,0.003426494,0.0008474833,0.001393136,0.0004775619,0.003791329,0.6343332,0.0003698783,0.3069233,0.002560037,0.04328318],"study_design_scores_gemma":[0.001334586,0.000190824,0.0006165853,0.00005670483,0.00009972475,0.000003400924,0.00006355319,0.9928826,0.00008212225,0.002071834,0.00221001,0.0003880319],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0278672,0.00003399222,0.9697836,0.0001201906,0.0002493963,0.0007008499,0.00003031201,0.0003224472,0.0008920116],"genre_scores_gemma":[0.9648529,0.00004248904,0.03348945,0.0001401028,0.00006645566,0.000003163834,0.0003888168,0.00002745874,0.0009891501],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9369857,"threshold_uncertainty_score":0.9999694,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1526840922283808,"score_gpt":0.2193846241840951,"score_spread":0.06670053195571435,"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."}}