{"id":"W4384616416","doi":"10.23952/jnva.7.2023.4.04","title":"Drop-DIP: A single-image denoising method based on deep image prior","year":2023,"lang":"en","type":"article","venue":"Journal of Nonlinear and Variational Analysis","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Overfitting; Artificial intelligence; Computer science; Deep learning; Pattern recognition (psychology); Noise reduction; Regularization (linguistics); Image (mathematics); Similarity (geometry); Noise (video); Machine learning; Artificial neural network","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001016309,0.001216117,0.001407608,0.0007822742,0.0003887229,0.0009170085,0.002331398,0.00154884,0.002874513],"category_scores_gemma":[0.002268318,0.000632456,0.001215377,0.0006436323,0.0008283786,0.001756373,0.001962543,0.002680443,0.001063619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007063837,"about_ca_system_score_gemma":0.001219011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002506293,"about_ca_topic_score_gemma":0.004052357,"domain_scores_codex":[0.9995602,0.00006173657,0.00002298964,0.0001020286,0.0002002651,0.0000527638],"domain_scores_gemma":[0.9993963,0.000165626,0.00005616657,0.000133017,0.0001862973,0.00006255254],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004635731,0.0002777999,0.001824689,0.0004113515,0.0002380671,0.0004339398,0.0001970116,0.3016918,0.06335843,0.02584098,0.01368951,0.5915729],"study_design_scores_gemma":[0.00002172199,0.00005187062,0.0001662918,0.00001260956,0.00002094527,0.0001297368,0.00001012216,0.9822891,0.01026161,0.004598841,0.002423506,0.00001364021],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003716959,0.0001473611,0.9945586,0.0001143215,0.00003660364,0.00003069683,0.00005131592,0.0006527518,0.0006912768],"genre_scores_gemma":[0.1589767,0.0006079542,0.8287894,0.0006993497,0.000124827,0.0001970483,0.0008334447,0.0007123964,0.009058772],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002874513,"threshold_uncertainty_score":0.009616256,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02209812782584662,"score_gpt":0.3168724519906422,"score_spread":0.2947743241647956,"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."}}