{"id":"W4391661581","doi":"10.1109/tetci.2024.3358200","title":"Joint Self-Supervised Enhancement and Denoising of Low-Light Images","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Emerging Topics in Computational Intelligence","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Carleton University","funders":"Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences; Chinese Academy of Sciences; National Natural Science Foundation of China","keywords":"Artificial intelligence; Computer science; Noise reduction; Computer vision; Color constancy; Noise (video); Pattern recognition (psychology); Feature (linguistics); Supervised learning; Global illumination; Image (mathematics); Artificial neural network","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":[0.0002979808,0.0001626804,0.0001656984,0.000423492,0.00008750901,0.0001224254,0.0003130259,0.00004811442,0.00003643226],"category_scores_gemma":[0.000006083945,0.000170302,0.00006285723,0.0005482543,0.00005442124,0.000452949,0.00001146178,0.0002350781,0.00001276508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000113177,"about_ca_system_score_gemma":0.00007842473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000179807,"about_ca_topic_score_gemma":0.000004454007,"domain_scores_codex":[0.9985098,0.00005436272,0.0004661569,0.0004216889,0.0003512561,0.0001967351],"domain_scores_gemma":[0.9994107,0.000162391,0.0000506886,0.0002284051,0.0001065446,0.00004126819],"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":[0.00001386169,0.0006229702,0.00001730452,0.0007097197,0.0001187373,0.00007072531,0.006583351,0.194846,0.02279666,0.0597743,0.0001784083,0.7142679],"study_design_scores_gemma":[0.00004297732,0.0000751462,0.00003046426,0.0003465638,0.000006018506,0.000007095864,0.00002992848,0.4888565,0.4962667,0.01407852,0.0001099009,0.00015016],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006613565,0.000328351,0.9903227,0.001421521,0.000597683,0.0001980707,0.000002716467,0.0002552658,0.0002601268],"genre_scores_gemma":[0.7790143,0.000184076,0.2205623,0.00008959381,0.00002324344,0.00002737507,7.321043e-7,0.000009432751,0.00008895311],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7724007,"threshold_uncertainty_score":0.6944715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02163919282556111,"score_gpt":0.2938804522355884,"score_spread":0.2722412594100273,"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."}}