{"id":"W4360827072","doi":"10.1186/s40537-023-00711-w","title":"Deep learning based deep-sea automatic image enhancement and animal species classification","year":2023,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Ichthyology and Marine Biology","field":"Environmental Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Centro para el Desarrollo Tecnológico Industrial; Ministerio de Ciencia, Innovación y Universidades","keywords":"Computer science; Artificial intelligence; Residual; Deep learning; Pipeline (software); Pattern recognition (psychology); Data set; Set (abstract data type); Convolutional neural network; Algorithm","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006591227,0.00006305272,0.0001115293,0.00005324215,0.00009356142,0.00001875992,0.0002929341,0.00004307379,0.0008172327],"category_scores_gemma":[0.000205978,0.00005025005,0.00001684627,0.0001220178,0.000146754,0.0002052316,0.0003553593,0.0001488504,0.0002960407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003775703,"about_ca_system_score_gemma":0.00001165932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001170526,"about_ca_topic_score_gemma":0.00005787033,"domain_scores_codex":[0.9992818,0.00008919636,0.0002172544,0.0001342421,0.0001352209,0.0001422661],"domain_scores_gemma":[0.9995019,0.00008148792,0.0001662827,0.00019119,0.000008741476,0.00005043689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000209897,0.0001831157,0.2632594,0.00005056012,0.00007550615,0.0001505208,0.0003893409,0.0002832701,0.4327768,0.00007454908,0.02007743,0.2824696],"study_design_scores_gemma":[0.0003561034,0.000281954,0.860217,0.000009875523,0.00003035532,0.00004394546,0.0001689931,0.1116876,0.0008751736,0.00007392238,0.02617035,0.00008479315],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9834175,0.00007005299,0.01203537,0.001756012,0.0003095865,0.00007411603,0.000006815417,0.00002429774,0.002306232],"genre_scores_gemma":[0.9968026,0.0001445447,0.002480838,0.0001017586,0.0001113767,0.000001071881,0.00007601889,0.000004843086,0.0002769271],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5969576,"threshold_uncertainty_score":0.8948125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06251843455730097,"score_gpt":0.2822145933443102,"score_spread":0.2196961587870092,"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."}}