{"id":"W3205781905","doi":"10.1109/icip46576.2022.9897680","title":"Deep Image Debanding","year":2022,"lang":"en","type":"preprint","venue":"2022 IEEE International Conference on Image Processing (ICIP)","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artifact (error); Deep learning; Artificial intelligence; Computer science; Construct (python library); Image (mathematics); Computer vision","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","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009466565,0.0007454489,0.0005789693,0.0008584559,0.0005386358,0.003181555,0.006259276,0.0002258525,0.002461987],"category_scores_gemma":[0.0002224807,0.0008116527,0.0002718646,0.0004456123,0.0002123828,0.001664433,0.003856519,0.002255497,0.0001702923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000955474,"about_ca_system_score_gemma":0.0007172668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006120635,"about_ca_topic_score_gemma":0.000009324175,"domain_scores_codex":[0.9943264,0.0002225838,0.0009029225,0.001824474,0.002007228,0.0007164403],"domain_scores_gemma":[0.9966663,0.0001038226,0.0009531442,0.001231999,0.0008811037,0.0001635885],"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":[0.0004247763,0.002549906,0.0003853705,0.001821012,0.0008504462,0.002398012,0.01104243,0.001392193,0.3033224,0.1322141,0.06641276,0.4771865],"study_design_scores_gemma":[0.0007411797,0.0002672366,0.0001317672,0.001143111,0.00005995422,0.00006716502,0.0003511828,0.8528514,0.07451932,0.06140835,0.006375183,0.002084166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007521567,0.0002010237,0.899748,0.003284352,0.005841647,0.0005485357,0.00003334342,0.001222153,0.08836877],"genre_scores_gemma":[0.6233538,0.0004456964,0.3596271,0.002388598,0.0009986922,0.001687194,0.0003814897,0.0001827108,0.01093469],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8514592,"threshold_uncertainty_score":0.9994335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06057705323253225,"score_gpt":0.3542322993571265,"score_spread":0.2936552461245942,"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."}}