{"id":"W4403759712","doi":"10.1007/978-3-031-72664-4_25","title":"Rejection Sampling IMLE: Designing Priors for Better Few-Shot Image Synthesis","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Prior probability; Shot (pellet); One shot; Image (mathematics); Sampling (signal processing); Artificial intelligence; Computer vision; Computer graphics (images); Algorithm; Bayesian probability","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001360969,0.0007219382,0.0006283101,0.001290653,0.0004862032,0.001707767,0.003206535,0.0003822757,0.000008073498],"category_scores_gemma":[0.0004611751,0.0006875711,0.0002225617,0.0008205103,0.0006407952,0.001614098,0.00142056,0.001016391,0.00002878827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006171627,"about_ca_system_score_gemma":0.0004667878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007183172,"about_ca_topic_score_gemma":0.000008783773,"domain_scores_codex":[0.9952391,0.00002584369,0.000669511,0.002366576,0.0008101287,0.0008887777],"domain_scores_gemma":[0.9964016,0.001334194,0.0003628291,0.001351803,0.0004063273,0.0001432311],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001061476,0.00001876867,0.000006035893,0.0003201654,0.0000206629,0.00005967889,0.0006124619,0.001524629,0.01955646,0.006370354,0.00007194831,0.9714282],"study_design_scores_gemma":[0.00009145331,0.0001222337,0.000005088102,0.001710396,0.000028148,0.0001026062,2.801382e-7,0.3772794,0.06636722,0.5515212,0.001861847,0.0009101757],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000009286185,0.0006283321,0.9936132,0.001160819,0.00152231,0.0007215922,0.000008407717,0.001138177,0.001197845],"genre_scores_gemma":[0.004405647,0.00003209426,0.9936019,0.000879777,0.0005796346,0.0001041752,0.000003292346,0.0001020411,0.0002914482],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9705181,"threshold_uncertainty_score":0.9995576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03425362563908926,"score_gpt":0.3043514396817086,"score_spread":0.2700978140426193,"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."}}