{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005133628,0.0003190148,0.0003976086,0.0003719559,0.0003289916,0.00112036,0.002534722,0.0002141833,0.0002550964],"category_scores_gemma":[0.0001019665,0.0004121209,0.0002724495,0.000888581,0.00005972026,0.001023323,0.002795254,0.0005540416,0.00007831703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000219306,"about_ca_system_score_gemma":0.000329047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001188566,"about_ca_topic_score_gemma":0.0002484227,"domain_scores_codex":[0.9976223,0.0001872111,0.0002655553,0.001405344,0.000106998,0.000412667],"domain_scores_gemma":[0.99793,0.0002175197,0.0003582991,0.0009374026,0.0003303105,0.0002265006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005030638,0.0009548932,0.00274518,0.000869861,0.0009681369,0.001545698,0.006610337,0.2811948,0.0005219371,0.5973054,0.01264148,0.09413923],"study_design_scores_gemma":[0.001502642,0.00007524702,0.0005139966,0.0003800011,0.0001015204,0.000008653289,0.0006836683,0.9130774,0.0003277153,0.06503576,0.01727222,0.001021191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01074885,0.0000312792,0.9617064,0.0003228844,0.0008317967,0.0007284653,0.00001707009,0.0002365571,0.02537671],"genre_scores_gemma":[0.9365481,0.0000525617,0.04929632,0.0006547651,0.0001024544,0.000009515737,0.0001775934,0.00003288738,0.0131258],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9257993,"threshold_uncertainty_score":0.9999166,"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."}}