{"id":"W2997820257","doi":"10.1609/aaai.v34i07.6628","title":"Diversity Transfer Network for Few-Shot Learning","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Transfer of learning; Classifier (UML); Negative transfer; Machine learning; Generative grammar; Feature vector; Code (set theory); Feature (linguistics); Task (project management)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004941205,0.0001940261,0.0002560288,0.00004597355,0.0009867039,0.0001881328,0.001743149,0.00008026844,0.00006963252],"category_scores_gemma":[0.0004831793,0.0001611585,0.0001763072,0.0006236819,0.0001467111,0.0003797794,0.0006636597,0.0003847771,0.00005203564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002419424,"about_ca_system_score_gemma":0.00005971043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001243929,"about_ca_topic_score_gemma":0.000003519847,"domain_scores_codex":[0.9983041,0.00002544627,0.0003837449,0.0004845108,0.0004221205,0.0003801337],"domain_scores_gemma":[0.9989424,0.0001523193,0.0001715015,0.0001336924,0.0004496471,0.0001503825],"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":[0.0001379155,0.00004366993,0.0007684461,0.00004552444,0.00002005715,3.428773e-7,0.008983558,0.003171059,0.007534443,0.9411345,0.0002997967,0.03786068],"study_design_scores_gemma":[0.0001632114,0.0009035384,0.0006608364,0.0002016991,0.0000408708,0.000002780556,0.00239074,0.7556307,0.1229845,0.1102786,0.006122415,0.0006201272],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06557938,0.00002778131,0.9076002,0.01388927,0.0004747632,0.0007161446,0.00000343472,0.0002660362,0.01144297],"genre_scores_gemma":[0.9925249,0.00001842544,0.005935295,0.001148378,0.0001421615,0.00001566534,5.996679e-7,0.00001179413,0.0002028323],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9269454,"threshold_uncertainty_score":0.7589028,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1675059434747592,"score_gpt":0.2909037532753881,"score_spread":0.123397809800629,"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."}}