{"id":"W4391697048","doi":"10.1109/tip.2024.3362153","title":"UCL-Dehaze: Toward Real-World Image Dehazing via Unsupervised Contrastive Learning","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":172,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; Shenzhen Science and Technology Innovation Program; National Defense Basic Scientific Research Program of China; Lingnan University; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Image editing; Embedding; Image (mathematics); Generalization; Leverage (statistics); Deep learning; Computer vision; Pattern recognition (psychology); Mathematics","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004711862,0.0004449171,0.0003526292,0.0007251224,0.0006455448,0.001798511,0.0007421912,0.0001028113,0.0001022188],"category_scores_gemma":[0.00001731548,0.0004494738,0.0001948541,0.001659383,0.0001855842,0.003809652,0.00001368253,0.00103063,0.0002202924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002620303,"about_ca_system_score_gemma":0.0002584505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009033078,"about_ca_topic_score_gemma":0.00003336962,"domain_scores_codex":[0.9970806,0.0001452364,0.0005251963,0.0009980578,0.0005528735,0.0006980964],"domain_scores_gemma":[0.9988453,0.0001928824,0.0001105418,0.0004107819,0.0002834884,0.00015697],"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":[0.0000286381,0.000144238,0.000005700404,0.0003783916,0.00005492444,0.0001911632,0.002602553,0.0002613786,0.3813348,0.0001551123,0.0002055004,0.6146376],"study_design_scores_gemma":[0.0003284032,0.0001313148,0.00003570845,0.000748451,0.00006184889,0.00003898628,0.0001201935,0.3416024,0.6550458,0.0005884283,0.0007403865,0.0005581049],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007930048,0.0003109986,0.987183,0.0007288659,0.0005928361,0.0003999594,0.000005912646,0.003990937,0.00599447],"genre_scores_gemma":[0.7714406,0.00009040889,0.2264341,0.0001649537,0.00009135491,0.0001204272,0.000002673767,0.00007439772,0.001581051],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7706476,"threshold_uncertainty_score":0.9997957,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0164759686231717,"score_gpt":0.2886161093988815,"score_spread":0.2721401407757099,"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."}}