{"id":"W2906191032","doi":"10.1109/cvpr.2019.00155","title":"Latent Filter Scaling for Multimodal Unsupervised Image-To-Image Translation","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"King Abdullah University of Science and Technology","keywords":"Computer science; Image translation; Artificial intelligence; Benchmark (surveying); Image (mathematics); Hyperparameter; Translation (biology); Code (set theory); Pattern recognition (psychology); Domain (mathematical analysis); Convolutional neural network; Filter (signal processing); Machine learning; Computer vision; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009746473,0.001029235,0.0006839283,0.0006465705,0.0003355967,0.0007834634,0.0008563563,0.00103729,0.004808637],"category_scores_gemma":[0.002759624,0.0003379226,0.0009288879,0.0007383726,0.0009987125,0.001143911,0.001270472,0.001690015,0.00215233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007359694,"about_ca_system_score_gemma":0.0004802155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00142762,"about_ca_topic_score_gemma":0.002326869,"domain_scores_codex":[0.999501,0.0001358275,0.00002083578,0.0001526275,0.0001397306,0.00004997973],"domain_scores_gemma":[0.9992847,0.0002937623,0.00007718927,0.0002049069,0.00009780957,0.00004172118],"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":[0.0003063738,0.0001828093,0.0008396317,0.0002716224,0.0001333044,0.0002401932,0.0002148966,0.5028484,0.08014027,0.04243185,0.009022579,0.3633681],"study_design_scores_gemma":[0.00001500898,0.00004574593,0.000214185,0.00001284101,0.00001360116,0.00009092625,0.00001543028,0.9706088,0.01258904,0.01368318,0.002697426,0.00001376739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00879295,0.0001925634,0.9876818,0.0001304521,0.0000339278,0.00003937218,0.0001038717,0.001038337,0.001986657],"genre_scores_gemma":[0.4635714,0.0005872235,0.5218344,0.0004665141,0.0001477574,0.0003063915,0.0009565732,0.000891867,0.01123785],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004808637,"threshold_uncertainty_score":0.01608646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03741701280440942,"score_gpt":0.2723589142469396,"score_spread":0.2349419014425302,"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."}}