{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003351363,0.001416277,0.001374433,0.001074156,0.0008045581,0.001151091,0.003711888,0.001923219,0.002521356],"category_scores_gemma":[0.01116967,0.0006030063,0.0008967368,0.001337503,0.001984435,0.005297642,0.003264885,0.003990747,0.001233067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001620313,"about_ca_system_score_gemma":0.001169471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002909816,"about_ca_topic_score_gemma":0.003046521,"domain_scores_codex":[0.9983583,0.0006435007,0.00005241097,0.0005588557,0.0002771395,0.0001097216],"domain_scores_gemma":[0.9950089,0.001994815,0.0004064333,0.001922223,0.0004554385,0.0002120455],"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":[0.0002905858,0.0006280881,0.002515349,0.0002851423,0.0001456184,0.0001900626,0.0004389734,0.4111062,0.01948543,0.04677959,0.007410206,0.5107248],"study_design_scores_gemma":[0.0000125382,0.00006080253,0.0002171918,0.000009599452,0.000007740834,0.00004338309,0.00002818771,0.9442517,0.00597808,0.04811466,0.001262613,0.00001359817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01406256,0.0001642315,0.9829146,0.0001783127,0.00003684885,0.0000517374,0.00009697386,0.001522016,0.0009726869],"genre_scores_gemma":[0.4356109,0.0002897316,0.5565034,0.0003982754,0.0001234127,0.0002972798,0.001201209,0.0004118066,0.005164005],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003711888,"threshold_uncertainty_score":0.01772392,"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."}}