{"id":"W3184153358","doi":"10.1109/tpami.2022.3201541","title":"Bayesian Embeddings for Few-Shot Open World Recognition","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Stanford University; National Aeronautics and Space Administration","keywords":"Artificial intelligence; Computer science; Open set; Embedding; Machine learning; Benchmark (surveying); Shot (pellet); Bayesian probability; Measure (data warehouse); Class (philosophy); Prior probability; Parametric statistics; Data mining; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001916896,0.001292171,0.001737046,0.001550732,0.0005597555,0.001827483,0.002873029,0.002056582,0.003217981],"category_scores_gemma":[0.009761062,0.0006913504,0.0009017969,0.001132905,0.001372357,0.00517433,0.002905725,0.003426183,0.001909179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001218288,"about_ca_system_score_gemma":0.0008710095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003433266,"about_ca_topic_score_gemma":0.004142809,"domain_scores_codex":[0.998436,0.0004104756,0.00007923672,0.0005597324,0.0003766793,0.0001377317],"domain_scores_gemma":[0.9966397,0.001406381,0.0003577574,0.0009466563,0.0004467333,0.0002027212],"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":[0.0004163068,0.0005237838,0.002621991,0.0002897575,0.0001352793,0.0001580865,0.0003094175,0.3031013,0.009184591,0.03571105,0.009831238,0.6377171],"study_design_scores_gemma":[0.000007413686,0.00004588722,0.0003477563,0.00001778624,0.000008268972,0.0000657925,0.00003347548,0.961939,0.002477861,0.03378009,0.001257432,0.00001927911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01389101,0.0005018907,0.9825433,0.0001975834,0.00005202604,0.00006947156,0.0002581795,0.001527208,0.0009593712],"genre_scores_gemma":[0.5565383,0.0008228982,0.431737,0.000556727,0.0002199034,0.0002988691,0.003511536,0.000499133,0.00581558],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003433266,"threshold_uncertainty_score":0.01076525,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05490974341790233,"score_gpt":0.3117677968617627,"score_spread":0.2568580534438604,"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."}}