{"id":"W4288075321","doi":"10.18280/ts.390333","title":"A Positive-Unlabeled Generative Adversarial Network for Super-Resolution Image Reconstruction Using a Charbonnier Loss","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Science Foundation of Zhejiang Province; National Social Science Fund of China; Natural Science Foundation of Shandong Province","keywords":"Discriminator; Artificial intelligence; Benchmark (surveying); Outlier; Computer science; Pattern recognition (psychology); Generative adversarial network; Image (mathematics); Similarity (geometry); Resolution (logic); Process (computing); Superresolution; Algorithm; Telecommunications","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005350368,0.0002044624,0.0002078093,0.0001172955,0.001093048,0.0001457847,0.0004557085,0.00003929378,0.0000859084],"category_scores_gemma":[0.0000194795,0.0002287937,0.0001008797,0.0004042925,0.0001143538,0.001022931,0.0002793256,0.0001913802,0.000001309672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004164438,"about_ca_system_score_gemma":0.000157904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001766344,"about_ca_topic_score_gemma":0.000002102165,"domain_scores_codex":[0.9981641,0.0001793661,0.0003341395,0.0005371097,0.0003414063,0.0004438609],"domain_scores_gemma":[0.9992811,0.00006487679,0.0002029314,0.0002082739,0.0001773546,0.00006546876],"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":[0.0009377101,0.0005065445,0.0002493708,0.00006282702,0.0002075252,0.00006776735,0.003556715,0.02617913,0.8466098,0.0329157,0.003167816,0.08553907],"study_design_scores_gemma":[0.001285468,0.0004111558,0.00005785024,0.00002999183,0.00003021772,0.0001153204,0.00005407126,0.9691213,0.01282116,0.01499994,0.0007463581,0.0003271328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01856634,0.00009007389,0.979179,0.0005627367,0.0004511577,0.0007480153,0.00004795016,0.0003015089,0.00005320978],"genre_scores_gemma":[0.1837637,0.000002705706,0.8150715,0.0003446812,0.0004633472,0.000280511,0.00002928401,0.00002040366,0.00002390132],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9429422,"threshold_uncertainty_score":0.9329935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01964329475485243,"score_gpt":0.2636504752874173,"score_spread":0.2440071805325648,"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."}}