{"id":"W3082546531","doi":"10.48550/arxiv.2009.00702","title":"Unsupervised Single-Image Reflection Separation Using Perceptual Deep Image Priors","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Artificial intelligence; Computer science; Image (mathematics); Pattern recognition (psychology); Deep learning; Reflection (computer programming); Prior probability; Convolutional neural network; Unsupervised learning; Process (computing); Perception; Computer vision; Machine learning; 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"],"consensus_categories":[],"category_scores_codex":[0.0002357977,0.0004665953,0.0003938551,0.0003846567,0.0002754271,0.0004478871,0.001624073,0.0003376203,0.00005917997],"category_scores_gemma":[0.00007452817,0.0006042327,0.0002435539,0.0009447588,0.0001635703,0.001773765,0.002029138,0.0007281061,0.0001333877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008600732,"about_ca_system_score_gemma":0.0002157651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001124649,"about_ca_topic_score_gemma":0.00002915258,"domain_scores_codex":[0.9971806,0.0002800672,0.0003280122,0.001562725,0.0002022749,0.000446293],"domain_scores_gemma":[0.9979499,0.00005598862,0.0003394521,0.001171273,0.0003109079,0.0001724899],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001831981,0.000579173,0.0007032325,0.000485745,0.0002146202,0.001244002,0.006630497,0.02205505,0.9365665,0.02717579,0.001250754,0.002911382],"study_design_scores_gemma":[0.0004526367,0.0001878629,0.0003418701,0.0001149178,0.0001066156,0.00001139232,0.000217526,0.9410158,0.04693407,0.0095696,0.0001895856,0.0008580721],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.217339,0.00001453258,0.7780911,0.0001114823,0.0003904646,0.0004726605,0.000004549681,0.001062888,0.002513345],"genre_scores_gemma":[0.8691974,0.00003143316,0.1301319,0.0001543649,0.0001360426,0.000001791363,0.00003439447,0.00003763958,0.0002750708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9189608,"threshold_uncertainty_score":0.9996409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1309766608532834,"score_gpt":0.2507466481951423,"score_spread":0.1197699873418588,"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."}}