{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004610022,0.0004207222,0.0004895062,0.0001748876,0.0001370196,0.0007114055,0.001151238,0.0002521104,0.0001149556],"category_scores_gemma":[0.0000522229,0.0003703689,0.0004057963,0.0001609286,0.00003007074,0.0005084489,0.0006849716,0.0002866973,0.0001947397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006356376,"about_ca_system_score_gemma":0.0001149489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000110965,"about_ca_topic_score_gemma":0.00001450152,"domain_scores_codex":[0.9974793,0.0001203182,0.0004742164,0.001125592,0.00030954,0.0004910075],"domain_scores_gemma":[0.998132,0.0002294126,0.0001247624,0.001007854,0.0003421183,0.0001638349],"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":[0.000155727,0.0002910856,0.0001051644,0.0005375434,0.00035183,0.00001110626,0.003632962,0.5913252,0.08137702,0.001039286,0.01524228,0.3059308],"study_design_scores_gemma":[0.0006033622,0.00005270579,0.000385594,0.00008625116,0.00003231404,7.40342e-7,0.00001318409,0.9781566,0.0173337,0.0009383374,0.001885832,0.0005113804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001221859,0.00006843574,0.9901128,0.003148285,0.001661774,0.001838144,0.00005903326,0.0001961486,0.001693556],"genre_scores_gemma":[0.19726,0.000013505,0.8008141,0.0006463405,0.0004027844,0.0001447894,0.00006951164,0.00003678152,0.0006121947],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3868314,"threshold_uncertainty_score":0.9998748,"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."}}