{"id":"W4389272191","doi":"10.1007/978-3-031-47966-3_18","title":"Unsupervised Deep-Learning Approach for Underwater Image Enhancement","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Underwater; Computer science; Artificial intelligence; Deep learning; Image (mathematics); Similarity (geometry); Ground truth; Inference; Computer vision; Image quality; Pattern recognition (psychology); Geology","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":[0.001622931,0.0007455401,0.0006669253,0.001061509,0.0004359268,0.0009584757,0.004218376,0.0003487474,0.00002624228],"category_scores_gemma":[0.0001071866,0.0006971804,0.0002265879,0.0007174458,0.0005713882,0.0009219481,0.002083034,0.0009045433,0.00008791772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004726817,"about_ca_system_score_gemma":0.0002867367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008837595,"about_ca_topic_score_gemma":0.000009490984,"domain_scores_codex":[0.9945925,0.00005192791,0.000697609,0.002300765,0.001191683,0.001165439],"domain_scores_gemma":[0.9972034,0.000423911,0.0003111584,0.001504557,0.0003925916,0.0001643601],"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":[0.00001754277,0.00009784044,0.00000895084,0.0003142728,0.00004726532,0.00006532,0.001597334,0.01307724,0.007796745,0.02032712,0.0001512664,0.9564991],"study_design_scores_gemma":[0.0004095093,0.0003790179,0.000007658939,0.000250353,0.00001370265,0.00001449439,4.669108e-7,0.8602879,0.04454212,0.09153997,0.001550394,0.001004414],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000007637326,0.0001288298,0.9904323,0.0003957135,0.0009410379,0.001359663,0.000003038128,0.0009632484,0.005768491],"genre_scores_gemma":[0.007973668,0.0000796168,0.9868526,0.0008215763,0.0003755478,0.0001898686,0.00003918375,0.0001011046,0.003566786],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9554947,"threshold_uncertainty_score":0.999548,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02205190317966191,"score_gpt":0.258757274960943,"score_spread":0.2367053717812811,"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."}}