{"id":"W2910601191","doi":"10.48550/arxiv.1901.02199","title":"FIGR: Few-shot Image Generation with Reptile","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Polytechnique Montréal","funders":"","keywords":"Shot (pellet); Computer science; Artificial intelligence; Benchmark (surveying); MNIST database; Image (mathematics); Novelty; Generative grammar; Set (abstract data type); Class (philosophy); Limiting; Field (mathematics); Domain (mathematical analysis); One shot; Deep learning; Machine learning; Computer vision; Pattern recognition (psychology); Cartography; Mathematics; Geography; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002200497,0.0003855844,0.0003801754,0.000167939,0.0001980832,0.0003409969,0.001352273,0.0002388518,0.0001158474],"category_scores_gemma":[0.00002270978,0.000376522,0.0001863155,0.0004298898,0.00009874423,0.0007729774,0.001198308,0.0004499453,0.0002530681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000159859,"about_ca_system_score_gemma":0.0002485566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001349605,"about_ca_topic_score_gemma":0.0000688925,"domain_scores_codex":[0.9976848,0.0002010087,0.0001919401,0.001408236,0.0001314508,0.0003825692],"domain_scores_gemma":[0.9975666,0.00006520699,0.0002818933,0.001666027,0.0002791352,0.0001411814],"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":[0.00002967358,0.0000747931,0.0004621113,0.00003632196,0.0001317784,0.0002590635,0.0001761617,0.9811251,0.001336499,0.01021996,0.005433007,0.0007154963],"study_design_scores_gemma":[0.0004002985,0.00009845892,0.0003228739,0.00005831773,0.00006752671,0.000007542665,0.00003059943,0.9932265,0.002463333,0.001263618,0.001511594,0.0005493421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03295923,0.00005148073,0.955575,0.0001559847,0.0007589523,0.0003911935,0.00001753891,0.0001739831,0.009916628],"genre_scores_gemma":[0.9770144,0.00009647538,0.01747546,0.0001566251,0.0003236498,0.000001783592,0.00004874568,0.00002579467,0.00485702],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9440552,"threshold_uncertainty_score":0.9998687,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0786742616169836,"score_gpt":0.1812348152687094,"score_spread":0.1025605536517258,"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."}}