{"id":"W2903204032","doi":"10.1109/cvprw.2019.00226","title":"Deep Graph Laplacian Regularization for Robust Denoising of Real Images","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Overfitting; Artificial intelligence; Computer science; Robustness (evolution); Laplacian matrix; Noise reduction; Convolutional neural network; Pattern recognition (psychology); Deep learning; Regularization (linguistics); Graph; Machine learning; Artificial neural network; Theoretical computer science","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":[0.001075228,0.0002631629,0.0004763122,0.0003234796,0.00009422088,0.000311409,0.001206684,0.0003025608,0.00000845674],"category_scores_gemma":[0.0001241447,0.0002481513,0.0002680415,0.0002687488,0.00005651265,0.000335159,0.0008101844,0.0002417309,0.000005456468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004377852,"about_ca_system_score_gemma":0.0001734702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001222848,"about_ca_topic_score_gemma":0.00001267576,"domain_scores_codex":[0.9979991,0.0002045627,0.0004794882,0.0006906099,0.0003257203,0.0003004686],"domain_scores_gemma":[0.9977322,0.0002652676,0.0003817353,0.001115111,0.0004447267,0.00006097393],"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":[0.00027549,0.0003707973,0.001065612,0.003545659,0.000476076,0.00003573517,0.003193813,0.3498453,0.05736199,0.2244947,0.006398471,0.3529364],"study_design_scores_gemma":[0.001325203,0.0001926033,0.001696977,0.0004236926,0.0001187605,0.00001533812,0.00004810172,0.6999943,0.1301356,0.1648777,0.0002403608,0.0009313567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003488983,0.0001953217,0.988127,0.0001942769,0.001020339,0.0005723329,0.000007215098,0.0001580162,0.009376585],"genre_scores_gemma":[0.01374911,0.00006779298,0.982793,0.0001208957,0.0001283943,0.00002048048,0.00004929691,0.00003013717,0.003040931],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.352005,"threshold_uncertainty_score":0.9999971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03029898487637205,"score_gpt":0.2856481989210645,"score_spread":0.2553492140446924,"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."}}