{"id":"W4398781982","doi":"10.1145/3665498","title":"Light-Aware Contrastive Learning for Low-Light Image Enhancement","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Feature (linguistics); Exploit; Computer vision; Noise (video); Image (mathematics); Global illumination; Pattern recognition (psychology); Regularization (linguistics); Representation (politics)","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","sts"],"consensus_categories":[],"category_scores_codex":[0.0003884315,0.0002577646,0.0002224992,0.0002764806,0.001311284,0.0004373366,0.001758546,0.00009232063,0.00001413702],"category_scores_gemma":[0.00003548538,0.0002642799,0.0001229627,0.0006271114,0.0001167548,0.0004253378,0.0001587886,0.0005112262,0.00007454395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001049273,"about_ca_system_score_gemma":0.0000867474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001078899,"about_ca_topic_score_gemma":0.000007444157,"domain_scores_codex":[0.9983068,0.0001026807,0.0004448303,0.0006190696,0.0001869615,0.0003396957],"domain_scores_gemma":[0.9961779,0.001395591,0.0001075557,0.001965067,0.0002371937,0.0001167461],"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":[0.00000531589,0.0004200744,0.00000417536,0.00009970988,0.0001085455,7.968463e-7,0.001568749,0.0001031968,0.03683962,0.009714453,0.000370801,0.9507645],"study_design_scores_gemma":[0.0004332793,0.0001797223,0.00003517553,0.0002985068,0.00006997855,0.00001002001,0.0002099524,0.7873454,0.06837357,0.003007164,0.1395692,0.0004680899],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001321743,0.0007326328,0.9868363,0.008990102,0.0001287645,0.001448725,0.00001539713,0.001170539,0.0005454177],"genre_scores_gemma":[0.5124652,0.000615071,0.4847121,0.0001477995,0.00006254224,0.001679476,0.0000392273,0.00002962072,0.0002489671],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9502965,"threshold_uncertainty_score":0.9999889,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01469163893558202,"score_gpt":0.3014922582023968,"score_spread":0.2868006192668148,"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."}}