{"id":"W3125751664","doi":"10.15353/jcvis.v6i1.3537","title":"Deep Residual Transform for Multi-scale Image Decomposition","year":2021,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Canada Research Chairs","keywords":"Computer science; Residual; Artificial intelligence; Leverage (statistics); Granularity; Transformation (genetics); Representation (politics); Pattern recognition (psychology); Hierarchy; Image (mathematics); Decomposition; Computer vision; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009885798,0.0001155055,0.0002621234,0.000163832,0.0001890617,0.000576976,0.0001989721,0.00002999182,0.000002078863],"category_scores_gemma":[0.00005703825,0.00009732924,0.0001233634,0.0001599052,0.00003515353,0.0009606797,0.00003591573,0.0001207991,0.00000208842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004048815,"about_ca_system_score_gemma":0.0001272036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003773887,"about_ca_topic_score_gemma":9.541583e-7,"domain_scores_codex":[0.9985635,0.000198391,0.0005509396,0.0001619164,0.0003712141,0.0001539861],"domain_scores_gemma":[0.998197,0.0003549939,0.0002557933,0.00009770952,0.0009880919,0.0001063931],"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":[0.0004909203,0.001044685,0.0007742696,0.0008202054,0.0002891058,0.0007345825,0.006882925,0.06040145,0.115884,0.01173525,0.01376096,0.7871817],"study_design_scores_gemma":[0.002626709,0.0001280895,0.003501487,0.0002225245,0.00002399317,0.002385226,0.0002607911,0.9788403,0.003958123,0.006427346,0.001464988,0.0001604077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003803771,0.001833696,0.9915056,0.001897289,0.0007190915,0.0001068366,0.000002995569,0.00001984358,0.0001108808],"genre_scores_gemma":[0.2302638,0.00002253332,0.7691206,0.0002975125,0.0002029602,0.00000228114,0.000006573704,0.00001021101,0.00007355032],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9184389,"threshold_uncertainty_score":0.5563793,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01968876424958521,"score_gpt":0.3453194604014362,"score_spread":0.325630696151851,"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."}}