{"id":"W4230576703","doi":"10.32920/ryerson.14657565.v1","title":"Large receptive field networks for accurate high-scale image super-resolution","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Convolutional neural network; Field (mathematics); Receptive field; Scale (ratio); Artificial intelligence; Image (mathematics); Network architecture; Pattern recognition (psychology); Superresolution; Mathematics; Cartography; Geography","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":[0.0004444214,0.0004004125,0.0004657026,0.000113673,0.000232289,0.0008274476,0.001689212,0.0004830989,0.00005721424],"category_scores_gemma":[0.0002494841,0.0003964395,0.0002165803,0.0002778284,0.00005135682,0.001173815,0.003682653,0.0008164158,0.000006834323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000157147,"about_ca_system_score_gemma":0.0002056108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007777997,"about_ca_topic_score_gemma":0.0001450939,"domain_scores_codex":[0.9973478,0.00009703873,0.0004390882,0.001237559,0.000244491,0.0006340272],"domain_scores_gemma":[0.9973774,0.0002733335,0.0002557872,0.00132015,0.0006685872,0.0001047444],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004031135,0.00214864,0.0002682252,0.00272739,0.0005885562,0.0002465808,0.008199275,0.01011847,0.03415623,0.08788723,0.4346553,0.4186009],"study_design_scores_gemma":[0.00035132,0.000122689,0.00004954085,0.0003369827,0.00002539113,0.0000087432,0.0001218349,0.9137505,0.03566698,0.04580834,0.002976082,0.0007815663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000200482,0.000479435,0.9926545,0.002517591,0.001060638,0.0007235447,0.00002116472,0.001438438,0.0009042102],"genre_scores_gemma":[0.03337923,0.0002134765,0.9635103,0.001248279,0.0002759292,0.0004586451,0.0001419869,0.00003866846,0.000733437],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.903632,"threshold_uncertainty_score":0.9998487,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01698943536220804,"score_gpt":0.3022474127319481,"score_spread":0.28525797736974,"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."}}