{"id":"W2798268958","doi":"10.1109/cvpr.2018.00837","title":"Matching Adversarial Networks","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Discriminator; Computer science; Generator (circuit theory); Ground truth; Task (project management); Artificial intelligence; Segmentation; Function (biology); Adversarial system; Matching (statistics); Image (mathematics); Generative grammar; Machine learning; Pattern recognition (psychology); Mathematics","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":[0.00006910377,0.0000437918,0.00004208786,0.00002294063,0.0001000306,0.00007348917,0.0003266362,0.00001326211,0.00009443046],"category_scores_gemma":[0.000004934793,0.00003538725,0.00001832465,0.0001245219,0.00002389292,0.000461079,0.0001892497,0.00004901026,0.0001939333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007594658,"about_ca_system_score_gemma":0.000008225205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001469928,"about_ca_topic_score_gemma":0.00000375207,"domain_scores_codex":[0.9995562,0.00001016745,0.00006637538,0.0001487209,0.00007570946,0.0001427727],"domain_scores_gemma":[0.9996716,0.00001945902,0.00001729992,0.0002199022,0.00002785902,0.00004386505],"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":[0.000004478365,0.00001513552,0.00009498261,7.835064e-7,0.000004206547,0.000005550063,0.0005428693,0.0004115304,0.0005241165,0.3230228,0.008062018,0.6673115],"study_design_scores_gemma":[0.0001960511,0.00003008821,0.0002603952,0.000006239594,5.850319e-7,0.000005314105,0.00002802051,0.9477016,0.0005393062,0.0190329,0.03209664,0.0001028762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003195436,0.000009628666,0.9563931,0.0003725144,0.001072658,0.00002179861,2.003346e-8,0.0001861085,0.04162461],"genre_scores_gemma":[0.5981748,0.000001881104,0.3987721,0.00190318,0.0003475941,5.061367e-7,1.083322e-7,0.000002754706,0.0007970991],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9472901,"threshold_uncertainty_score":0.2492685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008960901205130375,"score_gpt":0.2670858643970584,"score_spread":0.258124963191928,"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."}}