{"id":"W2917776700","doi":"10.48550/arxiv.1902.07104","title":"Adaptive Cross-Modal Few-Shot Learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Leverage (statistics); Artificial intelligence; Modalities; Discriminative model; Margin (machine learning); Machine learning; Metric (unit); Modal; Modality (human–computer interaction); Context (archaeology); Feature (linguistics); Feature learning; Focus (optics); Pattern recognition (psychology); Natural language processing","routes":{"ca_aff":true,"ca_fund":false,"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":[0.002566037,0.001242695,0.002397026,0.001926426,0.0006921049,0.001149339,0.003994653,0.001956533,0.002388691],"category_scores_gemma":[0.006820317,0.0006732852,0.001516942,0.001631924,0.001341624,0.003626346,0.002496931,0.002635015,0.0009034959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00115108,"about_ca_system_score_gemma":0.0008580862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002949051,"about_ca_topic_score_gemma":0.004162412,"domain_scores_codex":[0.9982789,0.0004934479,0.00008060165,0.0007094525,0.0002923298,0.0001454674],"domain_scores_gemma":[0.9973271,0.001393797,0.0002243549,0.0004595112,0.000405891,0.0001893961],"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":[0.0005916349,0.0009609091,0.005635412,0.0005648982,0.0005931761,0.0002681798,0.0005175311,0.372535,0.01630307,0.01529245,0.007600497,0.5791373],"study_design_scores_gemma":[0.0000107002,0.00007294441,0.0004686193,0.00001533525,0.00002460321,0.00006488416,0.00003028592,0.9859409,0.001885445,0.01091566,0.0005514725,0.00001912106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03008166,0.0009852513,0.9660167,0.0002131932,0.00007308514,0.000123176,0.000163149,0.001158797,0.00118493],"genre_scores_gemma":[0.7992342,0.0005318604,0.1919919,0.0007110552,0.0002217439,0.0003929541,0.001330144,0.0002642552,0.005321943],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003994653,"threshold_uncertainty_score":0.01357067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1125502070785356,"score_gpt":0.2191286905123671,"score_spread":0.1065784834338315,"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."}}