{"id":"W4297577962","doi":"10.48550/arxiv.2107.13682","title":"Bayesian Embeddings for Few-Shot Open World Recognition","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Aeronautics and Space Administration","keywords":"Open set; Embedding; Computer science; Artificial intelligence; Machine learning; Benchmark (surveying); Shot (pellet); Measure (data warehouse); Class (philosophy); Prior probability; Parametric statistics; Bayesian probability; Scheme (mathematics); Set (abstract data type); Data mining; Mathematics; Statistics; Geography","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":[0.002034565,0.001288412,0.001733601,0.001663624,0.0005978916,0.00178583,0.003069066,0.002283798,0.003132251],"category_scores_gemma":[0.01055884,0.0007521628,0.0009481221,0.0011918,0.001605378,0.005422387,0.003166139,0.003643793,0.001720649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001337761,"about_ca_system_score_gemma":0.0008549515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003320553,"about_ca_topic_score_gemma":0.00376874,"domain_scores_codex":[0.9983292,0.0004793243,0.00007832612,0.0006171585,0.0003622278,0.0001336671],"domain_scores_gemma":[0.9960817,0.001750644,0.0003896868,0.001110384,0.0004322409,0.0002353722],"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":[0.0004138936,0.0005412118,0.002967292,0.0003261448,0.000153267,0.0001731642,0.0003583602,0.3541067,0.00905957,0.04438514,0.01070912,0.5768062],"study_design_scores_gemma":[0.000007551882,0.00003756646,0.0003358792,0.00001624976,0.000007250616,0.00005656954,0.00003042834,0.9537217,0.002088453,0.04258032,0.001100556,0.00001739339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01479585,0.0004937959,0.9816949,0.0002328757,0.00004660473,0.00006403673,0.0002594999,0.001481596,0.0009308803],"genre_scores_gemma":[0.5828471,0.0007735612,0.4057242,0.0005470103,0.0002214949,0.0003012753,0.003418492,0.0004783305,0.005688472],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003320553,"threshold_uncertainty_score":0.01075989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1910433763099239,"score_gpt":0.2423231396736668,"score_spread":0.05127976336374288,"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."}}