{"id":"W4306411318","doi":"10.1016/j.knosys.2022.109997","title":"Degradation-aware and color-corrected network for underwater image enhancement","year":2022,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Underwater; Computer science; Artificial intelligence; Degradation (telecommunications); Computer vision; Image restoration; Sharpening; Channel (broadcasting); Convolutional neural network; Image (mathematics); Image processing; 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":[],"consensus_categories":[],"category_scores_codex":[0.0009218636,0.0002370978,0.0002907699,0.0001524423,0.0006665346,0.0002855561,0.000680404,0.000048452,0.00004234288],"category_scores_gemma":[0.00002418977,0.0002362124,0.00007266977,0.0005063671,0.0000490297,0.0002802294,0.000351489,0.0001472272,0.00002609174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000344304,"about_ca_system_score_gemma":0.0002056661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003902338,"about_ca_topic_score_gemma":0.00002706597,"domain_scores_codex":[0.997881,0.0003128168,0.0004242035,0.0005949665,0.0003029251,0.0004841005],"domain_scores_gemma":[0.9986226,0.0002703874,0.0001905996,0.0005738983,0.000254209,0.00008830986],"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":[0.000327519,0.001712385,0.002006249,0.001898911,0.0003153154,0.00005602693,0.003342965,0.004224737,0.07389776,0.04034866,0.8322296,0.0396399],"study_design_scores_gemma":[0.001582765,0.000910108,0.00008457692,0.0001503029,0.00003119235,0.0000147334,0.0001760818,0.7859461,0.04965802,0.0005361671,0.1602277,0.0006823294],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003104493,0.0007424527,0.9904174,0.0002703662,0.002294523,0.001719586,0.00001749251,0.000548067,0.0008856417],"genre_scores_gemma":[0.924667,0.000006329897,0.06284983,0.0002890781,0.0003024875,0.004918493,0.0001508556,0.00004976398,0.006766138],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9275675,"threshold_uncertainty_score":0.9632463,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01682529355455381,"score_gpt":0.2585572681739057,"score_spread":0.2417319746193519,"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."}}