{"id":"W2892122929","doi":"","title":"MetaGAN: an adversarial approach to few-shot learning","year":2018,"lang":"en","type":"article","venue":"Cambridge University Engineering Department Publications Database","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":283,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"Shot (pellet); Artificial intelligence; Computer science; Machine learning; Generator (circuit theory); Decision boundary; Adversarial system; Task (project management); Contextual image classification; Supervised learning; Simple (philosophy); One shot; Image (mathematics); Pattern recognition (psychology); Support vector machine; Engineering; Artificial neural network; Power (physics)","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":[0.002542263,0.001360585,0.001765207,0.0009569301,0.0004761812,0.00107069,0.002899726,0.002065602,0.002392225],"category_scores_gemma":[0.005490121,0.0007668834,0.001018904,0.000578589,0.001888273,0.002858039,0.003058125,0.003076405,0.0006218674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001066287,"about_ca_system_score_gemma":0.0007548634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001309715,"about_ca_topic_score_gemma":0.001737936,"domain_scores_codex":[0.9990017,0.000409039,0.00003172207,0.0002770686,0.0001860935,0.00009435832],"domain_scores_gemma":[0.9975459,0.001644737,0.0001683423,0.0003857296,0.0001500707,0.0001051137],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001981981,0.0001359524,0.001309847,0.0002016181,0.0001779363,0.0001548552,0.0001389316,0.7893047,0.005807046,0.06817741,0.004010639,0.1303828],"study_design_scores_gemma":[0.000004649003,0.00003071782,0.00008132061,0.000009806056,0.000006620117,0.00003546487,0.000005085443,0.9758448,0.000836245,0.02265439,0.000483012,0.000007837045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008069852,0.0003511554,0.9895107,0.0002796287,0.00005087413,0.00006114083,0.00007180151,0.0004512142,0.001153588],"genre_scores_gemma":[0.6454016,0.0006192558,0.3428693,0.001083579,0.0003142885,0.0004123959,0.0006754483,0.0003348204,0.008289278],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002899726,"threshold_uncertainty_score":0.0134449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02577113140306581,"score_gpt":0.2300618105105976,"score_spread":0.2042906791075318,"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."}}