{"id":"W2981988113","doi":"10.1109/iccv.2019.00028","title":"Learning Fixed Points in Generative Adversarial Networks: From Image-to-Image Translation to Disease Detection and Localization","year":2019,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"National Heart, Lung, and Blood Institute","keywords":"Image translation; Adversarial system; Computer science; Translation (biology); Artificial intelligence; Generative grammar; Image (mathematics); Computer vision; Pattern recognition (psychology)","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":[0.0002579661,0.0001844596,0.0001968899,0.0001621787,0.0001290988,0.0002825836,0.0001857998,0.00006243026,0.00008044894],"category_scores_gemma":[0.0001013729,0.000179565,0.0000436154,0.0005590017,0.00001831977,0.00103158,0.0001129569,0.0001289188,0.00008724007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006143763,"about_ca_system_score_gemma":0.00002862507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002598173,"about_ca_topic_score_gemma":0.0003414248,"domain_scores_codex":[0.9983879,0.0002864531,0.0002534515,0.0006132426,0.0001953888,0.000263531],"domain_scores_gemma":[0.9992665,0.0001330903,0.00005772359,0.0002362442,0.00009318091,0.0002132854],"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":[0.0002377356,0.00004442037,0.003560104,0.000006027443,0.00002109138,0.000007350588,0.002284421,0.8589756,0.0376339,0.0001386852,0.0001770106,0.09691367],"study_design_scores_gemma":[0.0006464628,0.0001171471,0.01585978,0.00002659182,0.00000893959,2.464241e-7,0.00008239998,0.978101,0.004178044,0.0002639636,0.0004811934,0.0002342191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05515427,0.00003327638,0.9428036,0.0006984022,0.0004270741,0.000555622,0.000002698414,0.00008699868,0.0002380602],"genre_scores_gemma":[0.8955897,0.00001170687,0.1034219,0.0006014105,0.0002136432,0.000022276,0.00001528992,0.00001409075,0.0001100191],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8404354,"threshold_uncertainty_score":0.7322448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007350359797905711,"score_gpt":0.2142151940228958,"score_spread":0.2068648342249901,"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."}}