{"id":"W4407264220","doi":"10.1016/j.neucom.2025.129572","title":"MDANet: A multi-stage domain adaptation framework for generalizable low-light image enhancement","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canada Research Chairs","funders":"Shenzhen Fundamental Research and Discipline Layout project","keywords":"Computer science; Adaptation (eye); Image (mathematics); Domain adaptation; Artificial intelligence; Domain (mathematical analysis); Stage (stratigraphy); Image enhancement; Computer vision; Pattern recognition (psychology); Mathematics; Optics; Physics; 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":[0.0004660995,0.0002626052,0.0002458317,0.0002763136,0.0003760487,0.0003574991,0.0009508821,0.00009144548,0.000009845462],"category_scores_gemma":[0.0001119085,0.0002805116,0.0001086942,0.0007299074,0.0000307817,0.0004370848,0.0004629452,0.0002152804,0.00001679711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001034763,"about_ca_system_score_gemma":0.00008289249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001267953,"about_ca_topic_score_gemma":0.000003201642,"domain_scores_codex":[0.9978353,0.0001057721,0.0004722016,0.0007582455,0.0002609702,0.0005675436],"domain_scores_gemma":[0.9987123,0.0002137424,0.0002154293,0.0006653621,0.0001340342,0.00005911848],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004413752,0.0006387457,0.0001371499,0.0006079566,0.00007280605,0.00005582527,0.002986673,0.003767093,0.481676,0.3738847,0.005825583,0.1303032],"study_design_scores_gemma":[0.0006079103,0.0001055528,0.0001092713,0.0002297257,0.000007361365,0.000001468246,0.0000355914,0.6224768,0.3468018,0.008152014,0.02116419,0.0003083923],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00425515,0.00008972675,0.9908082,0.001003266,0.0007144049,0.001094089,0.000002099972,0.0007077534,0.00132525],"genre_scores_gemma":[0.04488452,0.000009257492,0.9514596,0.00205977,0.0001136843,0.0001915665,0.000006343421,0.00002376425,0.001251524],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6187096,"threshold_uncertainty_score":0.9999647,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02864878368878971,"score_gpt":0.3190896335784755,"score_spread":0.2904408498896858,"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."}}